Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41467
    Prev
    Next
    INDEX
    Explanations

    ionic

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     достаточно
    -0.07
    [M
    -0.07
    [(
    -0.07
     Auf
    -0.07
    PAY
    -0.07
    經
    -0.06
    .MESSAGE
    -0.06
    (Properties
    -0.06
    Auf
    -0.06
     самых
    -0.06
    POSITIVE LOGITS
     bom
    0.08
     bogus
    0.07
     moons
    0.07
    ainment
    0.07
     Gibraltar
    0.07
    课本
    0.07
    畫
    0.07
     colleg
    0.07
     prudent
    0.07
    흭
    0.07
    Activations Density 0.004%

    No Known Activations