© 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. 56810
    Prev
    Next
    INDEX
    Explanations

    following verbs and nouns

    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
    unda
    -0.06
    enzi
    -0.06
     fri
    -0.06
    iba
    -0.06
    undo
    -0.06
    ä¹Łä¸İ
    -0.06
    omatic
    -0.05
    /t
    -0.05
    /J
    -0.05
    obo
    -0.05
    POSITIVE LOGITS
    ä¸Ģç»ıåıijçİ°
    0.09
     identified
    0.08
    identified
    0.08
    bable
    0.08
    并就
    0.08
    æĥħåĨµåIJİ
    0.08
    itle
    0.08
     пÑĥÑĤем
    0.08
    .GetEnumerator
    0.08
    usra
    0.08
    Activations Density 0.148%

    No Known Activations