© 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. 19719
    Prev
    Next
    INDEX
    Explanations

    measures of length

    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
    ÙĥرÙĬ
    -0.07
    æİĴéĻ¤
    -0.07
    ĤŃ
    -0.07
    onti
    -0.07
    зал
    -0.07
    iel
    -0.07
    æīĢæľī人
    -0.07
     cá»Ŀ
    -0.06
    ullo
    -0.06
    lector
    -0.06
    POSITIVE LOGITS
    èĬ±æŀľ
    0.07
    åį³çĶ¨
    0.07
     erg
    0.07
     gua
    0.07
    èIJ½æĪIJ
    0.07
    ighth
    0.06
    รà¹Īาà¸ĩ
    0.06
    ôs
    0.06
    ened
    0.06
    éĤµéĺ³
    0.06
    Activations Density 0.001%

    No Known Activations