© 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. 15463
    Prev
    Next
    INDEX
    Explanations

    another

    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
     launder
    -0.07
    鳜
    -0.07
    تكنولوج
    -0.07
    nelle
    -0.07
    -educated
    -0.07
    eks
    -0.07
    Raised
    -0.06
    -school
    -0.06
    เสม
    -0.06
     Turns
    -0.06
    POSITIVE LOGITS
    故乡
    0.08
     |↵
    0.07
    \Events
    0.07
     Tablet
    0.07
    ː
    0.07
    َ
    0.07
    必不可少
    0.06
    Blueprint
    0.06
    Wir
    0.06
    ­i
    0.06
    Activations Density 0.022%

    No Known Activations