© 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. 11183
    Prev
    Next
    INDEX
    Explanations

    prefix

    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
    æĶ¾çŁ¢
    -0.08
    heits
    -0.08
    lien
    -0.08
    acionais
    -0.08
    abouts
    -0.08
    spur
    -0.08
    ietet
    -0.08
    fram
    -0.07
    liest
    -0.07
    ilton
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    dorf
    0.09
    ivity
    0.09
    es
    0.08
    ़
    0.08
    NECT
    0.08
    less
    0.08
    ed
    0.08
    adecimal
    0.08
    tures
    0.08
    Activations Density 0.009%

    No Known Activations