© 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. 13493
    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
     tol
    -0.07
    ross
    -0.07
    orian
    -0.07
    ynet
    -0.07
    adis
    -0.07
    uki
    -0.07
     seedu
    -0.06
    rop
    -0.06
    Abb
    -0.06
    å¾ĢéĩĮ
    -0.06
    POSITIVE LOGITS
    dings
    0.09
    æĸ°æĿIJ
    0.08
    éĺ¶
    0.07
    script
    0.07
    alten
    0.07
    aight
    0.07
    imt
    0.07
     confirm
    0.07
    ALIGN
    0.07
    _WIDTH
    0.06
    Activations Density 0.000%

    No Known Activations