© 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. 118599
    Prev
    Next
    INDEX
    Explanations

    of

    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
    [:]↵
    -0.08
    (prod
    -0.08
    .ico
    -0.07
     starting
    -0.07
     hep
    -0.07
    מכון
    -0.07
    ことに
    -0.07
    exp
    -0.07
    Stmt
    -0.07
     canopy
    -0.07
    POSITIVE LOGITS
    ѽ
    0.08
     bigotry
    0.08
     yayg
    0.07
     Moses
    0.07
    ilingual
    0.07
    胥
    0.07
    𝙙
    0.07
    拘留
    0.07
    zerbai
    0.07
    雇主
    0.07
    Activations Density 0.003%

    No Known Activations