© 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. 31269
    Prev
    Next
    INDEX
    Explanations

    reduced-carrier transmission

    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
    lator
    -0.09
    elh
    -0.09
    ä¸ĭåIJĮ
    -0.09
    éĵģé¾Ļ
    -0.08
    lay
    -0.08
    odash
    -0.08
    رائ
    -0.08
    oard
    -0.08
    æľī车
    -0.08
    orthand
    -0.08
    POSITIVE LOGITS
    ya
    0.08
    **
    0.07
    åħ¶
    0.07
    ized
    0.07
    ä¸Ģ个
    0.06
    \v
    0.06
    \
    0.06
    ìķ¼
    0.06
    \[
    0.06
    书记
    0.06
    Activations Density 0.030%

    No Known Activations