© 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. 9604
    Prev
    Next
    INDEX
    Explanations

    build status badge

    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
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸
    -0.07
    ç»į
    -0.07
    _IMPORTED
    -0.07
     Ingy
    -0.07
    ishi
    -0.07
    令
    -0.06
    reme
    -0.06
    lei
    -0.06
    mento
    -0.06
     Dise
    -0.06
    POSITIVE LOGITS
    adr
    0.08
    åĥ¹
    0.07
    맼
    0.07
    chg
    0.07
    å¾·æĸ¯
    0.06
    brig
    0.06
    bron
    0.06
    ezz
    0.06
    çĶŁäº§åĬłå·¥
    0.06
    ixo
    0.06
    Activations Density 0.144%

    No Known Activations