© 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. 24365
    Prev
    Next
    INDEX
    Explanations

    waste and accumulated metabolic products

    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
    Missing
    -0.08
    ujan
    -0.08
     chôm
    -0.07
    _LOOKUP
    -0.07
     missing
    -0.07
     intimidated
    -0.07
    ebr
    -0.07
    umbed
    -0.07
    çıij
    -0.07
    rup
    -0.07
    POSITIVE LOGITS
    æİĴæ³Ħ
    0.13
     accumulated
    0.12
     accumulating
    0.12
     accumulation
    0.11
    æİĴåĩº
    0.11
     accumulate
    0.10
     Accum
    0.10
    åºŁçī©
    0.10
    积累
    0.10
    accum
    0.10
    Activations Density 0.066%

    No Known Activations