© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 28528
    Prev
    Next
    INDEX
    Explanations

    Multiple languages or code

    np_max-act · gemini-2.0-flash

    anonymized placeholder tokens and dataset-style formatting/markup within structured prompt–response or QA text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    奖励
    -0.07
    🍊
    -0.07
    中秋
    -0.07
    _uid
    -0.07
    ----------
    -0.07
     Hunters
    -0.07
    十万
    -0.07
    _TOKEN
    -0.07
     RNG
    -0.07
    _partner
    -0.07
    POSITIVE LOGITS
    �
    0.08
    交替
    0.07
     fo
    0.07
    roducing
    0.07
    活跃
    0.07
     Got
    0.07
     الاجتماعي
    0.07
     вот
    0.07
     cr
    0.07
     dot
    0.07
    Activations Density 0.359%

    No Known Activations