© 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. 49873
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    gado
    -0.08
    uliar
    -0.07
    culares
    -0.07
    lage
    -0.07
    gerufen
    -0.07
    æıIJåĩºçļĦéĹ®é¢ĺ
    -0.07
    uera
    -0.07
    sök
    -0.06
    pace
    -0.06
    å®Įä¹ĭåIJİ
    -0.06
    POSITIVE LOGITS
    attan
    0.08
    ambda
    0.08
    ãĤıãĤĬ
    0.07
    onta
    0.07
    è¦ģ好好
    0.06
    ाम
    0.06
    窪
    0.06
    ãģ®ãģĭãĤĤãģĹãĤĮ
    0.06
    ä¹Łæĺ¯æľĢ
    0.06
    AMP
    0.06
    Activations Density 0.005%

    No Known Activations