© 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. 41313
    Prev
    Next
    INDEX
    Explanations

    authors and literary works

    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
    è¯¥ç³»ç»Ł
    -0.08
    çıĪ
    -0.08
    çĶ±åħ¬åı¸
    -0.07
    çĶ±åIJĦ
    -0.07
    ZI
    -0.07
    ZR
    -0.07
    ä¹ĭ主
    -0.06
    @c
    -0.06
    ective
    -0.06
    çĻ¾äºĭ
    -0.06
    POSITIVE LOGITS
    ç¬Ķä¸ĭçļĦ
    0.11
    ç¬Ķä¸ĭ
    0.10
    enov
    0.09
    ÃŃsmo
    0.08
    arez
    0.08
    çŃī人çļĦ
    0.07
    riot
    0.07
    é£İæł¼çļĦ
    0.07
    -designed
    0.07
    baugh
    0.07
    Activations Density 0.195%

    No Known Activations