© 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. 62460
    Prev
    Next
    INDEX
    Explanations

    list notation and code

    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
     aç
    -0.07
    «
    -0.06
    oom
    -0.06
    andolo
    -0.06
    most
    -0.06
    å¿ħé¡»åħĪ
    -0.06
    cro
    -0.06
    éģ¿è®©
    -0.06
    rop
    -0.06
    <
    -0.06
    POSITIVE LOGITS
    _TAC
    0.08
    ä¸ĸ家
    0.08
    ansa
    0.08
    pper
    0.08
    æŁIJç§į
    0.08
    bito
    0.08
    vole
    0.07
    缸åħ³æݨèįIJ
    0.07
    vara
    0.07
    ä¼´ä½ł
    0.07
    Activations Density 0.010%

    No Known Activations