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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 112003
    Prev
    Next
    INDEX
    Explanations

    let

    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
     решил
    -0.08
     neighborhoods
    -0.07
    כתוב
    -0.07
     drawable
    -0.07
     disgusting
    -0.07
     fortunately
    -0.07
    authenticate
    -0.07
    onta
    -0.06
    /error
    -0.06
    certificate
    -0.06
    POSITIVE LOGITS
     One
    0.07
     })();↵
    0.06
    随时随
    0.06
     colleg
    0.06
    职称
    0.06
    학
    0.06
    技术
    0.06
    生產
    0.06
    喟
    0.06
    _diag
    0.06
    Activations Density 0.035%

    No Known Activations