© 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. 50761
    Prev
    Next
    INDEX
    Explanations

    codon

    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
    ometrics
    -0.09
    ulli
    -0.09
    oleon
    -0.08
    undef
    -0.08
    æ¥ł
    -0.08
    mtime
    -0.07
     episod
    -0.07
    ipse
    -0.07
     Horizont
    -0.07
    nis
    -0.07
    POSITIVE LOGITS
    ç¼ĸçłģ
    0.11
     coding
    0.09
     decoding
    0.09
     коди
    0.09
    coding
    0.09
     triplet
    0.09
     encoding
    0.09
    Coding
    0.08
     Coding
    0.08
     codes
    0.08
    Activations Density 0.010%

    No Known Activations