© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 126365
    Prev
    Next
    INDEX
    Explanations

    destruct

    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_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
    fos
    -0.08
    ?>
    ↵
    ↵
    -0.07
    graduate
    -0.07
    Vous
    -0.07
    {i
    -0.07
    研究院
    -0.07
    阁
    -0.07
    ఈ
    -0.06
     Jose
    -0.06
    -el
    -0.06
    POSITIVE LOGITS
     autob
    0.07
    BSITE
    0.07
     affiliated
    0.07
    .strings
    0.06
    agara
    0.06
     sạch
    0.06
    oples
    0.06
    中华文化
    0.06
    릉
    0.06
     hairstyles
    0.06
    Activations Density 0.006%

    No Known Activations