© 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. 32800
    Prev
    Next
    INDEX
    Explanations

    Rawlence, Williams, liberal models, phenomenologist

    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
    æŬ
    -0.08
    asonic
    -0.08
    oma
    -0.07
    è¿İ
    -0.07
    çĻ½èĬ±
    -0.07
    ä¸Ĭåı£
    -0.06
    oji
    -0.06
    itta
    -0.06
    ä¼ģåĪĴ
    -0.06
    åĨł
    -0.06
    POSITIVE LOGITS
     ÑĤеÑĤ
    0.08
     Covenant
    0.08
    æ´Ľåħĭ
    0.08
    æĵ¦èĤ©
    0.07
    houd
    0.07
    едÑĭ
    0.07
    .microsoft
    0.07
     covenant
    0.07
     ($.
    0.07
     Painter
    0.07
    Activations Density 0.002%

    No Known Activations