© 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. 15-RESID-POST-AA
    11. 60017
    Prev
    Next
    INDEX
    Explanations

    chat-formatting markers indicating the assistant’s role or the start of an assistant reply.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Try
    -0.07
    _rho
    -0.06
    ὃ
    -0.06
     mainBundle
    -0.06
    rf
    -0.06
    Memo
    -0.06
    غن
    -0.06
     goog
    -0.06
    íg
    -0.06
     posicion
    -0.06
    POSITIVE LOGITS
     capped
    0.08
     Listing
    0.07
     가능한
    0.06
    _li
    0.06
    /media
    0.06
    Ax
    0.06
     Lar
    0.06
     planta
    0.06
     Ket
    0.06
    启用
    0.06
    Activations Density 0.032%

    No Known Activations