© 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. 17204
    Prev
    Next
    INDEX
    Explanations

    encouragement / guidance

    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
    bestand
    -0.08
    éĢļçŁ¥æĪij们
    -0.08
    éĢĤåIJĪèĩªå·±çļĦ
    -0.08
    ÃŃp
    -0.07
    å°½èĩªå·±
    -0.07
    æıIJé«ĺèĩªå·±çļĦ
    -0.07
    _CREAT
    -0.07
    å½¼æѤ
    -0.07
    æľ¬æĬ¥åijĬ
    -0.07
    schlag
    -0.07
    POSITIVE LOGITS
    å¼ķ导
    0.11
    enc
    0.10
    é¼ĵåĬ±
    0.10
     encouragement
    0.09
     encour
    0.09
    çĤ¹æĭ¨
    0.09
    é¼ĵåĬ±åĴĮ
    0.08
     encourage
    0.08
     encouraging
    0.08
    诱导
    0.08
    Activations Density 0.058%

    No Known Activations