© 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. 50261
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving exponents

    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
    elok
    -0.07
    ed
    -0.07
    ation
    -0.06
    ÑĢÑģкого
    -0.06
    itud
    -0.06
    hren
    -0.06
    ure
    -0.06
    igon
    -0.06
    ä»İä»ĸ
    -0.06
    æ°´äºķ
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    köping
    0.08
    ornos
    0.08
    EA
    0.08
    ypy
    0.07
    Åijt
    0.07
    atform
    0.07
    æľĢæĸ°çīĪæľ¬
    0.07
     blat
    0.07
    åħ¶èģĮ
    0.07
    Activations Density 0.543%

    No Known Activations