© 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. 19-RESID-POST-AA
    11. 70839
    Prev
    Next
    INDEX
    Explanations

    SQL dialects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     הקוד
    -0.07
     Skull
    -0.07
    _DEVICE
    -0.07
    ḻ
    -0.07
    一阵
    -0.06
     ankles
    -0.06
     till
    -0.06
     intric
    -0.06
    뗴
    -0.06
    𬙊
    -0.06
    POSITIVE LOGITS
     instantiate
    0.07
    燚
    0.07
     dominate
    0.07
    Templates
    0.07
     baptism
    0.07
     aggressive
    0.06
    .ping
    0.06
    erp
    0.06
    <>(
    0.06
     depress
    0.06
    Activations Density 0.006%

    No Known Activations