© 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. 37998
    Prev
    Next
    INDEX
    Explanations

    only want

    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
     itself
    -0.10
    æľ¬èº«
    -0.09
    åĴ±ä»¬
    -0.08
    ieras
    -0.08
     dirinya
    -0.07
    ä¸ĢæĹ¦è¢«
    -0.07
    gerecht
    -0.07
    æľīåħ¶
    -0.07
    ucid
    -0.07
     theirs
    -0.07
    POSITIVE LOGITS
    ellet
    0.08
     ourselves
    0.08
     need
    0.08
    åĻ¨çŃī
    0.08
     have
    0.08
     know
    0.07
     yourself
    0.07
    /we
    0.07
    人æĹı
    0.07
     myself
    0.07
    Activations Density 0.316%

    No Known Activations