© 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. 28293
    Prev
    Next
    INDEX
    Explanations

    control algorithms and models

    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
    æĺ¯äººä½ĵ
    -0.08
    |string
    -0.07
    esture
    -0.07
    iaux
    -0.07
    utr
    -0.07
    æŃ»æ´»
    -0.07
    uale
    -0.07
    _touch
    -0.07
    egah
    -0.07
    ouched
    -0.07
    POSITIVE LOGITS
    xon
    0.08
    inaldo
    0.07
    orre
    0.07
    ç»ĦåIJĪ
    0.07
     combo
    0.07
    -like
    0.07
    ambul
    0.07
    éķĩä¸Ĭ
    0.06
    .only
    0.06
    éķĩ
    0.06
    Activations Density 0.003%

    No Known Activations