© 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. 23970
    Prev
    Next
    INDEX
    Explanations

    accumul

    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
    ÅĤaw
    -0.07
    bacher
    -0.07
    onato
    -0.07
     Gerr
    -0.07
    edah
    -0.07
    ɦ
    -0.06
    BOUND
    -0.06
    vale
    -0.06
    åĨ³ä¸į
    -0.06
    azah
    -0.06
    POSITIVE LOGITS
     acumul
    0.10
    累积
    0.09
     accumulated
    0.09
     accumulating
    0.08
     ÐĿако
    0.08
    umul
    0.08
    accum
    0.08
     acum
    0.08
     accum
    0.08
     Accum
    0.08
    Activations Density 0.001%

    No Known Activations