© 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. 62837
    Prev
    Next
    INDEX
    Explanations

    file format and type

    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
    FromArray
    -0.07
    使çĶ¨éģĵåħ·
    -0.07
    éĩijçīĽ
    -0.07
     unserialize
    -0.07
    åĽ¾åĨĮ
    -0.06
    ä½łæĺ¯æĪijçļĦ
    -0.06
    åĢŁæѤ
    -0.06
    Ñİз
    -0.06
    oft
    -0.06
    ixa
    -0.06
    POSITIVE LOGITS
    æł¼å¼ı
    0.08
     format
    0.07
     formats
    0.07
    /format
    0.07
     Format
    0.07
    é¹Ń
    0.07
    kv
    0.06
     formatted
    0.06
    åĬ±
    0.06
    åŀĤ缴
    0.06
    Activations Density 0.002%

    No Known Activations