© 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. 16563
    Prev
    Next
    INDEX
    Explanations

    accumulated data

    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
    ehn
    -0.09
    inker
    -0.08
    stantiate
    -0.08
    ontaine
    -0.07
    inkt
    -0.07
    loh
    -0.07
    ohn
    -0.07
    ä¸ĭæŬ
    -0.07
    akest
    -0.07
    edos
    -0.07
    POSITIVE LOGITS
     accumulated
    0.13
     accum
    0.13
    累积
    0.12
     stored
    0.12
     Accum
    0.12
     acumul
    0.12
    积累
    0.12
     accumulating
    0.11
     accumulation
    0.11
     accumulate
    0.11
    Activations Density 0.296%

    No Known Activations