© 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. 62863
    Prev
    Next
    INDEX
    Explanations

    binary digits and placeholders

    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
    ridor
    -0.08
    ×ķ×ĵ×Ķ
    -0.07
    ingleton
    -0.07
    è¿ĩ好
    -0.07
    ITION
    -0.07
    ividade
    -0.07
    iership
    -0.07
    eo
    -0.07
    åģıåģı
    -0.07
    leiding
    -0.07
    POSITIVE LOGITS
    immel
    0.07
    vey
    0.06
    èķī
    0.06
     deep
    0.06
    代表
    0.06
    uyu
    0.06
    代表çļĦ
    0.06
     sound
    0.06
    æŃ¥
    0.06
    å¿ĹåĪļ
    0.06
    Activations Density 0.032%

    No Known Activations