© 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. 39984
    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
    etz
    -0.08
     Omn
    -0.08
    гÑĢÑĭ
    -0.07
    æŃ»
    -0.07
    æį¨
    -0.07
    junk
    -0.07
     Rubin
    -0.07
     plata
    -0.07
     pitching
    -0.06
    å¹³åĿ¦
    -0.06
    POSITIVE LOGITS
    orted
    0.08
    ä¼¼ä¹İæĺ¯
    0.07
    禮
    0.07
     неÑĥдоб
    0.07
     oddly
    0.07
    æ´Ľä¼Ĭ
    0.07
    é¾ĻèĻİ
    0.07
    ×ķ×ļ
    0.07
    odd
    0.07
    merged
    0.07
    Activations Density 0.000%

    No Known Activations