© 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. 11-RESID-POST-AA
    11. 30268
    Prev
    Next
    INDEX
    Explanations

    aquatic exercise

    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
    ilm
    -0.07
    older
    -0.07
     Design
    -0.06
    DH
    -0.06
    Then
    -0.06
     mapping
    -0.06
    unque
    -0.06
    lower
    -0.06
     Fulton
    -0.06
     largely
    -0.06
    POSITIVE LOGITS
     hass
    0.07
    }));↵
    0.07
    司法
    0.07
     {};↵
    0.07
    antage
    0.07
    isce
    0.07
    如期
    0.06
    🍏
    0.06
    Runtime
    0.06
     }];↵
    0.06
    Activations Density 0.035%

    No Known Activations