© 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. 22650
    Prev
    Next
    INDEX
    Explanations

    chase and pursuit words

    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
    деÑģÑıÑĤ
    -0.09
    zinha
    -0.08
    istry
    -0.08
    veau
    -0.08
    åĮĸ管çIJĨ
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.08
    é¼İé¼İ
    -0.08
    ëĤĺê²Į
    -0.08
     Uniti
    -0.08
    ifies
    -0.08
    POSITIVE LOGITS
     dõi
    0.10
    ä¸įèĪį
    0.10
    追
    0.09
    ãĤĴ追
    0.08
    èĢħ们
    0.08
    æŁ»
    0.08
    追踪
    0.08
    追éĢIJ
    0.08
    ä¸įæĶ¾
    0.08
    worth
    0.08
    Activations Density 0.091%

    No Known Activations