© 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. 24409
    Prev
    Next
    INDEX
    Explanations

    erase a parameter

    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
    EXTERN
    -0.08
    waan
    -0.08
    ascin
    -0.08
    ilos
    -0.08
    齡
    -0.08
    otech
    -0.07
    AUSE
    -0.07
    otime
    -0.07
    gregate
    -0.07
     regia
    -0.07
    POSITIVE LOGITS
    pery
    0.07
    éħ¬
    0.07
    bear
    0.06
    aby
    0.06
    并ä¸Ķ
    0.06
    ukur
    0.06
    éĻ¤
    0.06
    ä¸Ķåľ¨
    0.06
    åģļèĩªå·±
    0.06
    å¿«åİ»
    0.06
    Activations Density 0.003%

    No Known Activations