© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62432
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥŀ
    -0.08
    halter
    -0.08
    anner
    -0.08
    dor
    -0.08
    elen
    -0.08
    esda
    -0.07
    æ·ĺ
    -0.07
    calc
    -0.07
    WB
    -0.07
    -pencil
    -0.07
    POSITIVE LOGITS
    ç¿Ķ
    0.07
    jej
    0.07
    íĸ¥
    0.07
     Bound
    0.06
    Bound
    0.06
    iego
    0.06
    åĢī
    0.06
    à·ıර
    0.06
    bell
    0.06
    ilien
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.