© 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. 15-RESID-POST-AA
    11. 119630
    Prev
    Next
    INDEX
    Explanations

    Court of Appeals documents

    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
    (d
    -0.07
     Petite
    -0.07
     pst
    -0.07
     בספר
    -0.07
     componentDidMount
    -0.07
    ăn
    -0.07
    头部
    -0.07
    /St
    -0.06
    versions
    -0.06
    fst
    -0.06
    POSITIVE LOGITS
    铯
    0.08
     LAS
    0.07
    IRO
    0.07
     Lucifer
    0.07
    alu
    0.07
    必须
    0.07
     Asi
    0.07
     distorted
    0.06
    elho
    0.06
    ipur
    0.06
    Activations Density 0.002%

    No Known Activations