© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 111642
    Prev
    Next
    INDEX
    Explanations

    in

    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
     assaults
    -0.06
     attack
    -0.06
    _LOG
    -0.06
     nostalg
    -0.06
    脫
    -0.06
    我会
    -0.06
    ิก
    -0.06
     overwhelm
    -0.06
    工具
    -0.06
     worksheet
    -0.06
    POSITIVE LOGITS
     Feinstein
    0.08
    澡
    0.07
     seit
    0.07
    belongsTo
    0.07
    магазине
    0.07
     Coca
    0.07
    TYPO
    0.07
     bei
    0.07
    crud
    0.07
    UIScrollView
    0.07
    Activations Density 0.102%

    No Known Activations