© 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. 32579
    Prev
    Next
    INDEX
    Explanations

    synonym endings `-ion`, `-in`, `-at`, `-an`

    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
    æĢ§å¼º
    -0.07
    fici
    -0.06
    è¾¾æĭī
    -0.06
    емÑĭ
    -0.06
    åĩºä¸į
    -0.06
    ìĿ¸ëĵ¤ìĿ´
    -0.06
    esimo
    -0.06
    ä¸į欲
    -0.06
    ritos
    -0.06
    licit
    -0.06
    POSITIVE LOGITS
    0.09
    gend
    0.08
    <tool_response>
    0.08
    ithe
    0.07
    clude
    0.07
    ughter
    0.07
    çıĬ
    0.07
    ënd
    0.07
    ollar
    0.07
    uang
    0.07
    Activations Density 0.722%

    No Known Activations