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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13401
    Prev
    Next
    INDEX
    Explanations

    url

    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
    呸
    -0.06
    对你
    -0.06
    吩咐
    -0.06
    绗
    -0.06
     Account
    -0.06
    对自己的
    -0.06
     Naughty
    -0.06
     Fund
    -0.06
     çalıştı
    -0.06
    全自动
    -0.06
    POSITIVE LOGITS
     -.
    0.07
     Flesh
    0.07
    .primary
    0.07
     '');
    0.06
     puck
    0.06
    .JFrame
    0.06
    %);↵
    0.06
     Москов
    0.06
     literacy
    0.06
    istency
    0.06
    Activations Density 0.088%

    No Known Activations