© 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. 58529
    Prev
    Next
    INDEX
    Explanations

    hydro conversion

    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
    ught
    -0.08
    kite
    -0.07
    çĺ¦
    -0.07
    寺
    -0.07
    self
    -0.07
    æıIJé«ĺèĩªèº«
    -0.07
    Composite
    -0.07
    çĭ¬èĩª
    -0.07
    èĩªä½ľ
    -0.07
    å¯ĨåĪĩéħįåIJĪ
    -0.06
    POSITIVE LOGITS
    _convert
    0.09
    NOP
    0.09
     fully
    0.08
    Fully
    0.08
    uddy
    0.08
    æĿ¾è½¯
    0.08
    Conversion
    0.07
     converting
    0.07
    _CONVERT
    0.07
    软çļĦ
    0.07
    Activations Density 0.021%

    No Known Activations