© 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. 32735
    Prev
    Next
    INDEX
    Explanations

    doi citations

    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
    stime
    -0.08
    elic
    -0.08
    èĥ½å¤ŁæĽ´å¥½åľ°
    -0.08
    inned
    -0.08
    äºĤ
    -0.07
    moc
    -0.07
    à¸Ħà¸Ńย
    -0.07
    hini
    -0.07
    oad
    -0.07
    åŁİåħ³
    -0.07
    POSITIVE LOGITS
    opus
    0.08
     Leading
    0.07
     NRF
    0.06
     journal
    0.06
    yles
    0.06
    omia
    0.06
    åĪĨç±»åı·
    0.06
    æĪĺæ³ķ
    0.06
     refere
    0.06
    artin
    0.06
    Activations Density 0.081%

    No Known Activations