© 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. 7447
    Prev
    Next
    INDEX
    Explanations

    collect terms with powers

    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
    thon
    -0.08
    uan
    -0.08
    _COMPILE
    -0.08
    å¾·éŁ³
    -0.08
    çĶŁæ´»åľĪ
    -0.07
    wort
    -0.07
    ä¸ĭæĮ«
    -0.07
    صب
    -0.07
    egi
    -0.07
    éģĵéģĵ
    -0.07
    POSITIVE LOGITS
    è¿Ļä¹Īç®Ģåįķ
    0.08
    attles
    0.07
    çļĦåįķ
    0.07
    legant
    0.07
    æľŁä¸º
    0.07
     Cro
    0.07
    oker
    0.07
    QUEUE
    0.07
    Closure
    0.07
    åļ£
    0.07
    Activations Density 0.020%

    No Known Activations