© 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. 18116
    Prev
    Next
    INDEX
    Explanations

    guitar, gaga, sha512

    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
    cind
    -0.09
    kof
    -0.09
    tese
    -0.08
    xfan
    -0.08
    oogle
    -0.08
    istrator
    -0.08
    SSION
    -0.08
    auft
    -0.08
    Æ°á»Łng
    -0.08
    phem
    -0.07
    POSITIVE LOGITS
     iconic
    0.07
    ix
    0.07
    orte
    0.06
     widespread
    0.06
     bow
    0.06
     пÑĢиÑĩ
    0.06
     coming
    0.06
    лÑĸ
    0.06
     Gene
    0.06
     morph
    0.06
    Activations Density 0.013%

    No Known Activations