© 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. 64776
    Prev
    Next
    INDEX
    Explanations

    expansion

    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
    uman
    -0.08
    ä»İéĩį
    -0.07
     Salon
    -0.07
    èĩªä¸ª
    -0.07
    Ïĥι
    -0.07
    uÄį
    -0.07
     telemetry
    -0.07
    éĨį
    -0.06
    ghost
    -0.06
    éĿĴèįī
    -0.06
    POSITIVE LOGITS
    Expansion
    0.08
    ç«ĭ
    0.08
     Expansion
    0.08
    ustum
    0.08
    outu
    0.08
    -expanded
    0.07
     expansion
    0.07
    expand
    0.07
    çĻ»è®°è¯ģ
    0.07
    -expand
    0.07
    Activations Density 0.003%

    No Known Activations