© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12011
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes or fragments

    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
    thon
    -0.06
     Web
    -0.06
    翱ç¿Ķ
    -0.06
    agrid
    -0.06
     awe
    -0.06
     span
    -0.06
    被åħ³éĹŃ
    -0.06
    ukur
    -0.06
    è¸ı
    -0.06
     ref
    -0.06
    POSITIVE LOGITS
    elib
    0.08
    bens
    0.08
    é»į
    0.08
    anken
    0.08
    enstein
    0.08
    aney
    0.08
    æİĴ头
    0.08
    åĽ½å®¶å®īåħ¨
    0.08
    mouseenter
    0.08
    æ¡©
    0.08
    Activations Density 0.011%

    No Known Activations