© 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. 37921
    Prev
    Next
    INDEX
    Explanations

    gentle cleaning actions

    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
     cynical
    -0.07
    cop
    -0.06
     hollow
    -0.06
    éĵ¸éĢł
    -0.06
     stable
    -0.06
    stable
    -0.06
     Hollow
    -0.06
    ä¸į稳å®ļ
    -0.06
    ehm
    -0.06
    éľ²
    -0.06
    POSITIVE LOGITS
     gentle
    0.12
    gent
    0.11
     Gentle
    0.11
    è½»æŁĶ
    0.10
     gently
    0.10
     gent
    0.10
    温åĴĮ
    0.09
    çĽĸä¸ĸ
    0.09
    使çĶ¨åīį
    0.09
    æĹ¶ä½¿çĶ¨
    0.09
    Activations Density 0.017%

    No Known Activations