© 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. 32802
    Prev
    Next
    INDEX
    Explanations

    official documents and reports

    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
    cola
    -0.08
    åıĹçĸ«æĥħå½±åĵį
    -0.08
    cule
    -0.08
    æĿİè½»
    -0.07
    Ä©
    -0.07
    å¾Īç´¯
    -0.07
    åīĬ
    -0.07
    ìĹŃìĿĦ
    -0.07
    举éŨ
    -0.07
    bene
    -0.07
    POSITIVE LOGITS
    é¼ĵåĬ±
    0.10
    纲é¢Ĩ
    0.10
     encouraging
    0.09
    åı·åı¬
    0.08
    åįģæĿ¡
    0.08
     encourages
    0.08
     encourage
    0.08
    åĬŀåħ¬åİħ
    0.08
    缮æłĩåĴĮ
    0.08
    æĪĺçķ¥çĽ®æłĩ
    0.08
    Activations Density 0.154%

    No Known Activations