© 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. 49601
    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
    <|box_end|>
    -0.11
    αι
    -0.07
    ÙĩÛĮ
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    иÑģÑĤеÑĢ
    -0.07
    ifié
    -0.07
    Ø©
    -0.07
    \xa
    -0.07
    ippy
    -0.07
    æĭ©
    -0.07
    POSITIVE LOGITS
    ori
    0.08
    or
    0.07
    ored
    0.07
    o
    0.07
     vs
    0.07
    æłı
    0.07
     ->
    0.06
    ëŀĮ
    0.06
    ovan
    0.06
    æIJ
    0.06
    Activations Density 0.000%

    No Known Activations