© 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. 12378
    Prev
    Next
    INDEX
    Explanations

    et al

    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
    juh
    -0.08
    çķĮ
    -0.08
    ë²Į
    -0.07
    IKA
    -0.07
    çķĮçļĦ
    -0.07
    history
    -0.07
    çļĦå¿ĥéĩĮ
    -0.07
    Ïĩη
    -0.07
    θÏħ
    -0.07
    鸳
    -0.06
    POSITIVE LOGITS
    Öģ
    0.08
    riff
    0.07
     Claro
    0.07
    dam
    0.06
    ucci
    0.06
    raid
    0.06
    ield
    0.06
    praak
    0.06
    áv
    0.06
    æĭīæĭī
    0.06
    Activations Density 0.062%

    No Known Activations