© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62883
    Prev
    Next
    INDEX
    Explanations

    score or position

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ç»ĺ
    -0.07
    rena
    -0.07
    è±Ĩ
    -0.07
    enho
    -0.07
    /classes
    -0.07
    ä¸įè´Ł
    -0.06
    éĥ¨éŨ
    -0.06
    .au
    -0.06
    éķ¿å¤Ħ
    -0.06
    opro
    -0.06
    POSITIVE LOGITS
    errupted
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.07
    ä¸Ĭä¸Ģ
    0.07
    继ç»Ńä¿ĿæĮģ
    0.07
     next
    0.07
    usat
    0.07
    ä¸ĭä¸Ģ
    0.07
     luck
    0.07
    ä¸Ĭè¿Ľ
    0.07
     excess
    0.06
    Activations Density 0.003%

    No Known Activations