© 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. 23824
    Prev
    Next
    INDEX
    Explanations

    tactics using tempo and aggression

    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
    éĶµ
    -0.08
    追溯
    -0.07
    为äºĨ满足
    -0.07
     tros
    -0.07
     Loving
    -0.07
    让人们
    -0.06
    ç¿ĺ
    -0.06
    iecz
    -0.06
     cof
    -0.06
    åĭī
    -0.06
    POSITIVE LOGITS
     tact
    0.14
     tactics
    0.14
     tactical
    0.14
    ç»Ļ对æĸ¹
    0.14
    æĪĺæľ¯
    0.13
    对æĸ¹çļĦ
    0.13
     opponent
    0.12
    让对æĸ¹
    0.12
     Tactics
    0.11
     opponents
    0.11
    Activations Density 0.104%

    No Known Activations