© 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. 38286
    Prev
    Next
    INDEX
    Explanations

    definite integral

    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
    uzzi
    -0.07
    ril
    -0.07
    ä¸Ģä¾ĭ
    -0.07
    åºĶå½ĵåIJij
    -0.07
    人以ä¸ĭ
    -0.07
    æľĪä¸ĭæŬ
    -0.06
    acht
    -0.06
    _DOT
    -0.06
    åĬªåĬĽåģļåĪ°
    -0.06
    åı¯çĶ¨æĢ§
    -0.06
    POSITIVE LOGITS
    åĮºéĹ´
    0.10
     interval
    0.10
     span
    0.09
     Interval
    0.09
    -span
    0.08
    .interval
    0.08
    interval
    0.08
     구ê°Ħ
    0.08
    èµ·æŃ¢
    0.08
    ToFit
    0.08
    Activations Density 0.011%

    No Known Activations