© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23255
    Prev
    Next
    INDEX
    Explanations

    field or method name

    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
    ì°©
    -0.08
    çĥŃçĪ±ç¥ĸåĽ½
    -0.08
    hoff
    -0.07
     te
    -0.06
     повеÑĢ
    -0.06
    主è¦ģå°±æĺ¯
    -0.06
    aupt
    -0.06
     vin
    -0.06
    éķij
    -0.06
    æĥ°
    -0.06
    POSITIVE LOGITS
     bul
    0.08
    ?action
    0.08
     wise
    0.07
    led
    0.07
    enz
    0.07
    缺å¸Ń
    0.07
    .localized
    0.07
    深港
    0.07
    oja
    0.07
    spi
    0.07
    Activations Density 0.159%

    No Known Activations