© 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. 1503
    Prev
    Next
    INDEX
    Explanations

    normally

    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¸İåĽ½éĻħ
    -0.08
    counter
    -0.08
    _counter
    -0.07
    Counter
    -0.07
     counter
    -0.07
     Counter
    -0.07
    å°Ķæĸ¯
    -0.07
    Ĭ
    -0.07
    åįĥ家
    -0.07
    jec
    -0.06
    POSITIVE LOGITS
     Normally
    0.11
     normally
    0.11
    æŃ£å¸¸æĥħåĨµä¸ĭ
    0.11
    normally
    0.10
    ä½Ĩå½ĵ
    0.09
    Normally
    0.09
     ordinarily
    0.08
    ä½Ĩèĭ¥
    0.08
    ä½Ĩå¦Ĥæŀľ
    0.08
    æŃ£å¸¸çļĦ
    0.08
    Activations Density 0.275%

    No Known Activations