© 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. 13380
    Prev
    Next
    INDEX
    Explanations

    accumulated, accrued, cumulative

    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
    çĭĤå¦Ħ
    -0.08
     doomed
    -0.07
    èIJ¨æĸ¯
    -0.07
    åį³çĶ¨
    -0.07
    icc
    -0.07
    aldo
    -0.07
    /GPL
    -0.07
    stroy
    -0.07
    jaw
    -0.07
    éĹŃä¸Ĭ
    -0.07
    POSITIVE LOGITS
     accumulated
    0.17
    累积
    0.13
    积累äºĨ
    0.12
     accum
    0.12
     accrued
    0.11
    accum
    0.11
    积累çļĦ
    0.11
     Accum
    0.11
     cumulative
    0.11
    ç´¯ç©į
    0.11
    Activations Density 0.320%

    No Known Activations