© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    integration and summation

    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
    INET
    -0.07
    .ident
    -0.07
    hk
    -0.07
    leter
    -0.07
    æĥĭæĥľ
    -0.07
     silenced
    -0.06
    齿
    -0.06
    olos
    -0.06
    onis
    -0.06
    haw
    -0.06
    POSITIVE LOGITS
    cum
    0.09
     accum
    0.09
    ç©į
    0.09
    累积
    0.08
     accumulated
    0.08
     accumulation
    0.08
     accumulating
    0.08
     acumul
    0.08
    累计
    0.08
     Cum
    0.08
    Activations Density 0.005%

    No Known Activations