© 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. 32838
    Prev
    Next
    INDEX
    Explanations

    and then other

    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
    ãĢijãĢIJ
    -0.08
    obie
    -0.08
    /respond
    -0.08
    ')['
    -0.08
    å¿ĹåĪļ
    -0.07
    ä¸İæ²»çĸĹ
    -0.07
    ffel
    -0.07
    uves
    -0.07
    /reset
    -0.07
    æľ¬åŃIJ
    -0.07
    POSITIVE LOGITS
    /or
    0.09
     hence
    0.07
     probably
    0.07
    æĺ¯ä¸ĢèĪ¬
    0.07
    åIJĮæĹ¶å¯¹
    0.07
    далее
    0.07
    /of
    0.07
    other
    0.06
     compliment
    0.06
    à¥į
    0.06
    Activations Density 1.855%

    No Known Activations