© 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. 45581
    Prev
    Next
    INDEX
    Explanations

    binomial and multinomial coefficients

    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
    gaste
    -0.07
    egos
    -0.07
    å¤ĸéĢģ
    -0.07
    åį¿
    -0.07
    æµ·éģĵ
    -0.06
     xÃł
    -0.06
    ä¸Ģæī«
    -0.06
    AlmostEqual
    -0.06
    egot
    -0.06
    ggio
    -0.06
    POSITIVE LOGITS
     Crédit
    0.07
     tá»Ń
    0.07
    DU
    0.07
    æŶæĹł
    0.07
    abaj
    0.07
    ิà¸ĩ
    0.07
    azer
    0.07
    -thinking
    0.06
    inne
    0.06
    çĸij
    0.06
    Activations Density 0.003%

    No Known Activations