© 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. 64700
    Prev
    Next
    INDEX
    Explanations

    induction problems

    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
    åĪĨéĴŁåīį
    -0.08
    åªĽ
    -0.07
    isy
    -0.07
     sẵn
    -0.07
    æĦŁåįģ足
    -0.07
    uss
    -0.07
     heti
    -0.07
     <<
    -0.07
     Zit
    -0.07
    .CopyTo
    -0.07
    POSITIVE LOGITS
    å¤įæĿĤ度
    0.08
     complexity
    0.08
    T
    0.07
    _cases
    0.07
    éĺĻ
    0.07
    çĶ¨æ°´éĩı
    0.07
    ç©·
    0.07
     Wed
    0.06
    çµ
    0.06
     cạn
    0.06
    Activations Density 0.002%

    No Known Activations