© 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. 1453
    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
    è¾Ł
    -0.07
    æľªå®Įå¾ħç»Ń
    -0.07
     Crow
    -0.06
    ifar
    -0.06
    æĦ£
    -0.06
     Bates
    -0.06
    unky
    -0.06
     “
    -0.06
     inout
    -0.06
    Crow
    -0.06
    POSITIVE LOGITS
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.09
    aro
    0.08
    )::
    0.08
    ваÑĩ
    0.08
    _raise
    0.08
    empa
    0.08
    سخ
    0.08
    -process
    0.07
    å¦Ĥæľīä¾µæĿĥ
    0.07
    Dup
    0.07
    Activations Density 0.000%

    No Known Activations