© 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. 62468
    Prev
    Next
    INDEX
    Explanations

    services and licenses

    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
    agged
    -0.07
    çĪ±æĥľ
    -0.07
    .gov
    -0.06
    æĭĽæłĩç½ij
    -0.06
     Giz
    -0.06
    æĽ´æĺĵ
    -0.06
    æī¬
    -0.06
     vs
    -0.06
    大èĩ´
    -0.06
    æľ¬æĿ¥å°±
    -0.06
    POSITIVE LOGITS
    çĸijéļ¾
    0.11
    åĪĨæŀIJåıĬ
    0.09
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.09
    åıĬåIJĦç§į
    0.09
    çIJĨ论ä¸İ
    0.09
    åıĬéħįå¥Ĺ
    0.09
    çļĦåIJĦç±»
    0.09
    åıĬè¦ģæ±Ĥ
    0.08
    çŃīåIJĦç±»
    0.08
    åıĬ缸åħ³
    0.08
    Activations Density 0.674%

    No Known Activations