© 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. 18537
    Prev
    Next
    INDEX
    Explanations

    limit towards infinity

    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
    å·²äºİ
    -0.07
    omu
    -0.07
    çľ¼ä¸ĭ
    -0.07
    å½ĵåħ¶
    -0.07
    åį³æĹ¥èµ·
    -0.06
    aney
    -0.06
    ä»ĬçĶŁ
    -0.06
    èĩªåı¤
    -0.06
    å½ĵä»ĸ
    -0.06
    mouseout
    -0.06
    POSITIVE LOGITS
    Ø¡
    0.07
    raje
    0.07
    .mit
    0.07
    æݥ触åĪ°
    0.07
    gos
    0.07
    agas
    0.07
    éĿłæĭ¢
    0.07
    ough
    0.07
    li
    0.07
    æ§ĭ
    0.07
    Activations Density 0.004%

    No Known Activations