© 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. 58466
    Prev
    Next
    INDEX
    Explanations

    special characters or Chinese

    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
    (___
    -0.09
    .Ultra
    -0.09
    çĤľ
    -0.08
    /logger
    -0.08
    vecs
    -0.08
    δε
    -0.08
    ="__
    -0.08
    igno
    -0.08
    äºĨä»Ģä¹Ī
    -0.08
    erva
    -0.08
    POSITIVE LOGITS
    æľ¬é¢ĺ
    0.10
    é¢ĺå¹²
    0.09
    æķħ
    0.09
    æķħéĢī
    0.09
    æľ¬é¢ĺèĢĥæŁ¥
    0.09
    æľ¬é¢ĺçŃĶæ¡Ī
    0.08
    é¢ĺæĦı
    0.07
     Comm
    0.06
    èĢĥæŁ¥
    0.06
    ir
    0.06
    Activations Density 0.002%

    No Known Activations