© 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. 32092
    Prev
    Next
    INDEX
    Explanations

    loops and iterations

    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
    å°Ķå¾·
    -0.08
    Ĺı
    -0.08
     Ehr
    -0.07
    åIJİæľŁçļĦ
    -0.07
    äºĨ解èĩªå·±
    -0.07
    _reordered
    -0.07
    awei
    -0.07
    amt
    -0.07
     sophistic
    -0.06
    idak
    -0.06
    POSITIVE LOGITS
    éģįåİĨ
    0.09
    éģį
    0.09
    å·¡
    0.08
    åĩ¡æĺ¯
    0.08
     forEach
    0.08
    èµ°éģį
    0.08
    .forEach
    0.08
    avanaugh
    0.08
    ocs
    0.08
    unos
    0.08
    Activations Density 0.145%

    No Known Activations