© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15862
    Prev
    Next
    INDEX
    Explanations

    what it means

    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
    åľ°å¤´
    -0.09
    edor
    -0.08
    .Promise
    -0.08
    æŁIJç§į
    -0.08
    tures
    -0.07
    ategoria
    -0.07
    mary
    -0.07
    endente
    -0.07
    å©´
    -0.07
    ections
    -0.07
    POSITIVE LOGITS
    ±
    0.07
    äºİè¡Į
    0.07
    åĬłæĭ¿å¤§
    0.07
    æĸ°åĬłåĿ¡
    0.07
    o
    0.07
     exactly
    0.07
    åĪ°ä½İ
    0.06
    uage
    0.06
    ley
    0.06
     bort
    0.06
    Activations Density 0.157%

    No Known Activations