© 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. 7-RESID-POST-AA
    11. 59421
    Prev
    Next
    INDEX
    Explanations

    articles

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    สมา
    -0.07
     bells
    -0.07
    שמו
    -0.07
    _sig
    -0.07
    深切
    -0.07
     למ
    -0.07
     Scheme
    -0.06
    ఆ
    -0.06
     נכונה
    -0.06
     testcase
    -0.06
    POSITIVE LOGITS
    ASY
    0.07
     heavyweight
    0.07
     società
    0.07
    יר
    0.06
    _Callback
    0.06
     pushed
    0.06
     faire
    0.06
    Have
    0.06
    威胁
    0.06
    周刊
    0.06
    Activations Density 0.008%

    No Known Activations