© 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. 50950
    Prev
    Next
    INDEX
    Explanations

    include

    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
    paring
    -0.07
    -login
    -0.07
    .Compile
    -0.07
     представлен
    -0.06
    <System
    -0.06
     concurrency
    -0.06
    䲢
    -0.06
    AutoresizingMask
    -0.06
    .pe
    -0.06
    𨱑
    -0.06
    POSITIVE LOGITS
     Flooring
    0.08
     الرحمن
    0.07
     Explain
    0.07
     roy
    0.07
     ALLOW
    0.07
     EXP
    0.07
     Robert
    0.07
     rehab
    0.07
     SAF
    0.07
    地板
    0.07
    Activations Density 0.008%

    No Known Activations