© 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. 15793
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    agi
    -0.06
    ulers
    -0.06
    è§ģéĿ¢
    -0.06
    ilia
    -0.06
    ![
    -0.06
    ilh
    -0.06
     Binder
    -0.06
    azy
    -0.06
    ilah
    -0.05
    reise
    -0.05
    POSITIVE LOGITS
    æĮĸæİĺåħ¬åı¸
    0.08
    PROTO
    0.08
    éªĭ
    0.08
     geared
    0.08
    endregion
    0.08
    æĺ¾å¾ĹæĽ´åĬł
    0.08
    æīĭæı¡
    0.07
    adou
    0.07
    .deploy
    0.07
    纯æŃ£
    0.07
    Activations Density 0.084%

    No Known Activations