© 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. 89322
    Prev
    Next
    INDEX
    Explanations

    Sherbrooke or places ending -brook/-bourne

    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
    …↵↵↵↵
    -0.08
    …”
    -0.08
    耗费
    -0.07
    contexts
    -0.07
    本身就是
    -0.07
    ในฐานะ
    -0.07
    .getResult
    -0.07
     не
    -0.07
    ((_
    -0.07
    🎩
    -0.07
    POSITIVE LOGITS
    ですね
    0.08
     supervised
    0.07
     mView
    0.07
     Spect
    0.07
     banks
    0.07
     drops
    0.07
     copies
    0.07
    /s
    0.07
     Enforcement
    0.07
     converters
    0.07
    Activations Density 0.001%

    No Known Activations