© 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. 13455
    Prev
    Next
    INDEX
    Explanations

    solid/liquid processing

    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
    ä¸İåIJĪä½ľ
    -0.08
    åħ¶ä¸İ
    -0.07
    ä¸İæĮijæĪĺ
    -0.07
    ä¸İæĸ¹æ³ķ
    -0.07
    ä¸İåIJĦ
    -0.07
    ArrayOf
    -0.07
    ä¸İ被
    -0.07
    ä¸İéĿŀ
    -0.07
    cion
    -0.07
    quisition
    -0.07
    POSITIVE LOGITS
    gether
    0.09
    åħ³ç³»ä¸Ń
    0.09
     relationship
    0.09
    åħ³ç³»
    0.08
     relationships
    0.08
    çļĭ
    0.08
    åħ³ç³»çļĦ
    0.08
    ä¹ĭéĻħ
    0.08
    ä¸Ģä½ĵæľº
    0.08
    ä¹ĭ交
    0.08
    Activations Density 0.152%

    No Known Activations