© 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. 60454
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
     sting
    -0.07
    -j
    -0.07
    å°ļ
    -0.06
    жин
    -0.06
     вÑģ
    -0.06
    åijIJ
    -0.06
    é¦
    -0.06
    zu
    -0.06
    ych
    -0.06
    çĿ¡çľł
    -0.06
    POSITIVE LOGITS
    मान
    0.08
    ãĥijãĥ¼ãĤ¯
    0.08
    irates
    0.08
    umos
    0.08
    Scaled
    0.08
    å¸ĥ伦
    0.08
    emap
    0.08
    ôn
    0.08
     paraz
    0.08
    amenti
    0.07
    Activations Density 0.064%

    No Known Activations