© 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. 66709
    Prev
    Next
    INDEX
    Explanations

    atur/natur

    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
    Deposit
    -0.07
    שמש
    -0.07
    oming
    -0.07
    inois
    -0.07
     parc
    -0.07
    AS
    -0.07
     العملات
    -0.07
    的记忆
    -0.07
     Whilst
    -0.07
     own
    -0.06
    POSITIVE LOGITS
    狻
    0.08
     Ży
    0.08
    atur
    0.07
     patiënt
    0.07
    从而使
    0.07
    aturing
    0.07
    |.
    0.07
    _IMETHOD
    0.07
     aut
    0.07
    cout
    0.07
    Activations Density 0.024%

    No Known Activations