© 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. 63513
    Prev
    Next
    INDEX
    Explanations

    unread emails

    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
    æķħåIJį
    -0.08
    inale
    -0.07
    ä¹ĭä¹ħ
    -0.07
    ç¨ĭ度çļĦ
    -0.07
    å¾ij
    -0.07
    .spring
    -0.06
    .Must
    -0.06
    emt
    -0.06
    è¿Ļ个社ä¼ļ
    -0.06
    继ç»Ń使çĶ¨
    -0.06
    POSITIVE LOGITS
    èĪį
    0.08
     CIC
    0.07
    æļ
    0.07
    /epl
    0.07
     Gest
    0.06
    ä¸Ģæĸij
    0.06
    ayah
    0.06
     ninh
    0.06
    yson
    0.06
     fitting
    0.06
    Activations Density 0.034%

    No Known Activations