© 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. 50854
    Prev
    Next
    INDEX
    Explanations

    chef, .com, /problems, clarfg

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Ner
    -0.07
    姿
    -0.07
    ä¸ĭåĿ¡
    -0.07
    s
    -0.06
    ecc
    -0.06
    semb
    -0.06
     koy
    -0.06
    æIJıæĸĹ
    -0.06
    èĪŁå±±
    -0.06
    oll
    -0.06
    POSITIVE LOGITS
    onti
    0.09
    blr
    0.09
    stown
    0.08
    rega
    0.08
    stime
    0.08
    å½Ŀ
    0.08
    Ĥ¬
    0.08
    áĤı
    0.07
    WXYZ
    0.07
    èĬĿåĬł
    0.07
    Activations Density 0.001%

    No Known Activations