© 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. 18983
    Prev
    Next
    INDEX
    Explanations

    apologies

    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
    Âł
    -0.07
    天å¸Ī
    -0.06
    -master
    -0.06
    ç¿°
    -0.06
    ä¼ļæľīä¸Ģ个
    -0.06
    çļĦä¸ĢèĪ¬
    -0.06
    éĥ½æľīä¸Ģ个
    -0.06
    å¤ĸåĬł
    -0.06
    çļĦè¿Ļä¸Ģ
    -0.06
    an
    -0.06
    POSITIVE LOGITS
    PackageName
    0.08
    quine
    0.08
    ourd
    0.08
     scop
    0.08
    ç®Ģæ´ģ
    0.08
    reto
    0.08
    éģ¿åħį
    0.08
    å®ŀåIJį认è¯ģ
    0.07
    éģ¿åħįåĩºçİ°
    0.07
    igy
    0.07
    Activations Density 0.006%

    No Known Activations