© 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 EvalsExportsAPI 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. 77156
    Prev
    Next
    INDEX
    Explanations

    Pop

    np_max-act · gemini-2.0-flash
    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
    (tmp
    -0.07
    候选
    -0.07
    ῡ
    -0.07
    �
    -0.07
    舾
    -0.07
    腾
    -0.07
    andidates
    -0.07
    ?v
    -0.06
    体系
    -0.06
     Burns
    -0.06
    POSITIVE LOGITS
     blackjack
    0.08
    /tutorial
    0.07
    _printf
    0.07
    .Maybe
    0.07
     preprocess
    0.07
    התנהגות
    0.07
    _contents
    0.07
    OMETRY
    0.06
    <|im_end|>
    0.06
     Luther
    0.06
    Activations Density 0.001%

    No Known Activations