© 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. 11024
    Prev
    Next
    INDEX
    Explanations

    configuration

    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
    杀
    -0.08
     velocity
    -0.08
     killed
    -0.08
     asn
    -0.07
    صال
    -0.07
     Work
    -0.07
     exception
    -0.07
    病毒
    -0.07
     sur
    -0.07
    /qu
    -0.07
    POSITIVE LOGITS
     configuration
    0.08
    ">${
    0.07
     porch
    0.07
    ,height
    0.06
    argc
    0.06
    friend
    0.06
    [][]
    0.06
    器件
    0.06
    宏伟
    0.06
     imageSize
    0.06
    Activations Density 0.031%

    No Known Activations