© 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. 1529
    Prev
    Next
    INDEX
    Explanations

    programming data types

    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
    rog
    -0.08
    åıĬè¦ģæ±Ĥ
    -0.07
    è¶Ĭ
    -0.07
    elog
    -0.07
    GRE
    -0.07
    åĴĮè¦ģæ±Ĥ
    -0.07
    è¶Ĭæĺ¯
    -0.06
    hani
    -0.06
    è¶Ĭå¿«
    -0.06
    atform
    -0.06
    POSITIVE LOGITS
    zilla
    0.09
    aturen
    0.07
    rown
    0.07
    ÃŃsmo
    0.07
    åħīèį£
    0.07
    eram
    0.07
    uchos
    0.06
    _BOUNDS
    0.06
    js
    0.06
    .prototype
    0.06
    Activations Density 0.020%

    No Known Activations