© 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. 11982
    Prev
    Next
    INDEX
    Explanations

    ip address and file extensions

    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
    arf
    -0.08
    é¦Ļå¥Ī
    -0.07
    ourcem
    -0.07
    iform
    -0.07
    _fmt
    -0.07
    çļĦ好åıĭ
    -0.07
     Capit
    -0.07
    jected
    -0.07
    جÙĬ
    -0.07
    emat
    -0.07
    POSITIVE LOGITS
    举åŁİ
    0.07
    vel
    0.07
    /***/
    0.07
    æŀī
    0.07
    寸
    0.07
    åĨįèµ·
    0.07
    æĻĭ级
    0.07
    Sessions
    0.06
     gou
    0.06
    设
    0.06
    Activations Density 0.120%

    No Known Activations