© 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. 51461
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    foy
    -0.07
    afa
    -0.07
    bies
    -0.07
    бан
    -0.06
    lash
    -0.06
    ắc
    -0.06
    æģĭæĥħ
    -0.06
    stil
    -0.06
    hez
    -0.06
    var
    -0.06
    POSITIVE LOGITS
    (SS
    0.07
    entic
    0.06
    alin
    0.06
    ithub
    0.06
    -keys
    0.06
     ÑĢÑĥко
    0.06
    æķ¦
    0.06
    åĪ®
    0.06
    åĻ¨
    0.06
    -thinking
    0.06
    Activations Density 0.000%

    No Known Activations