© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18539
    Prev
    Next
    INDEX
    Explanations

    number

    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
     Millennium
    -0.07
    flash
    -0.07
    [opt
    -0.07
    国有资产
    -0.07
     orgy
    -0.06
    rgyz
    -0.06
     Ore
    -0.06
     jade
    -0.06
    /*----------------------------------------------------------------
    -0.06
     Fem
    -0.06
    POSITIVE LOGITS
    🌪
    0.08
    دان
    0.07
    プログ
    0.07
     ************************
    0.07
    '])↵
    0.07
     verwendet
    0.07
    오는
    0.07
    應用
    0.07
    lords
    0.06
    얊
    0.06
    Activations Density 0.001%

    No Known Activations