© 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. 37977
    Prev
    Next
    INDEX
    Explanations

    variants of things

    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¢
    -0.07
    viso
    -0.07
    interop
    -0.07
     exponent
    -0.06
    compat
    -0.06
     Lester
    -0.06
    rava
    -0.06
     inorder
    -0.06
    .defaults
    -0.06
    æ½Ł
    -0.06
    POSITIVE LOGITS
     outliers
    0.09
     outlier
    0.08
    æĬľãģij
    0.08
     Sampling
    0.07
    æ¡ĥæĿİ
    0.07
    çĮĽè¿Ľ
    0.07
     legitimately
    0.07
    ä¸į代表
    0.07
     sampling
    0.07
    éĩĩæł·
    0.07
    Activations Density 0.058%

    No Known Activations