© 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. 22237
    Prev
    Next
    INDEX
    Explanations

    odd and even numbers

    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
    èĮ´
    -0.09
    ansir
    -0.08
    /rc
    -0.07
    åĬłåħ¥ä¹¦çŃ¾
    -0.07
    eted
    -0.07
    terek
    -0.07
    çĢ¬
    -0.07
    PTY
    -0.07
    ׳×Ļ×Ļ×Ŀ
    -0.07
    交åıīè·¯åı£
    -0.07
    POSITIVE LOGITS
    _scr
    0.07
    ged
    0.07
    gaard
    0.07
    idian
    0.07
    otty
    0.07
    å¾Īæ·±
    0.06
    ella
    0.06
     impre
    0.06
    upil
    0.06
    AAF
    0.06
    Activations Density 0.005%

    No Known Activations