© 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. 48258
    Prev
    Next
    INDEX
    Explanations

    links and email addresses

    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
    าà¸ļ
    -0.08
    .transforms
    -0.08
    ಳ
    -0.08
    éĹ®åĮ»çĶŁ
    -0.08
    _LEN
    -0.08
    วล
    -0.08
    ç§ijåѦä¸İæĬĢæľ¯
    -0.07
    <?,
    -0.07
    ายà¸Ļ
    -0.07
    autoload
    -0.07
    POSITIVE LOGITS
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    0.10
    _LENGTH
    0.10
    à¹Ģà¸ŀ
    0.08
    รà¸ģ
    0.08
    ì¤ijìķĻ
    0.07
    å·¥ä½ľå§Ķåijĺä¼ļ
    0.07
     kec
    0.07
    éĽĨåĽ¢æľīéĻIJ责任åħ¬åı¸
    0.07
     |/
    0.07
    è¿ijå¹³
    0.07
    Activations Density 4.367%

    No Known Activations