© 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. 25036
    Prev
    Next
    INDEX
    Explanations

    numbers and 'ukas'

    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
    æŃ£éģĵ
    -0.07
    erton
    -0.07
    大éĥ¨ä»½
    -0.07
    umah
    -0.07
    ĤŃ
    -0.07
    antos
    -0.07
    andex
    -0.07
    TD
    -0.07
    è¯ij
    -0.07
    对æłĩ
    -0.07
    POSITIVE LOGITS
    apg
    0.07
    .ua
    0.07
     salva
    0.07
    dan
    0.07
    łíĮ
    0.07
    urada
    0.07
     Gare
    0.07
    好å¿ĥæĥħ
    0.07
    _BOTH
    0.07
    gó
    0.07
    Activations Density 0.014%

    No Known Activations