© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14879
    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
    eges
    -0.09
    ogne
    -0.08
    acman
    -0.08
    adoo
    -0.08
    Categ
    -0.08
    verno
    -0.08
    ados
    -0.08
     fant
    -0.07
    éļıä¹ĭ
    -0.07
    odob
    -0.07
    POSITIVE LOGITS
    aidu
    0.07
    terra
    0.06
    éĩį伤
    0.06
     deduction
    0.06
    []=
    0.06
    nesc
    0.06
    mend
    0.06
    addListener
    0.06
     -->
    0.06
    asha
    0.06
    Activations Density 0.000%

    No Known Activations