© 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. 41700
    Prev
    Next
    INDEX
    Explanations

    worldwide, royalty-free license

    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
    ityEngine
    -0.09
     INGR
    -0.08
     izman
    -0.08
    ä¸įèĩªç¦ģ
    -0.08
    lasan
    -0.08
     asisti
    -0.08
    marshall
    -0.08
    äºĭåįĬåĬŁåĢį
    -0.08
    bstract
    -0.08
    ãĥ¯ãĤ¯ãĥģãĥ³
    -0.08
    POSITIVE LOGITS
    ag
    0.07
    erna
    0.07
    ig
    0.07
    oy
    0.06
    esse
    0.06
    oug
    0.06
    ç¦ģæŃ¢è½¬è½½
    0.06
    ä
    0.06
    åªĽ
    0.06
    èİ«éĿŀ
    0.06
    Activations Density 0.434%

    No Known Activations