© 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. 49871
    Prev
    Next
    INDEX
    Explanations

    bromides

    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
    ../../../
    -0.08
    à¤Ĺत
    -0.07
    nev
    -0.07
    রি
    -0.07
    rais
    -0.07
    resh
    -0.07
    áĥ£áĥł
    -0.07
    ervlet
    -0.07
    resse
    -0.07
    ral
    -0.07
    POSITIVE LOGITS
    avais
    0.09
    éħ¸éĴ¾
    0.08
    شت
    0.08
     Frieden
    0.07
    edList
    0.07
    itten
    0.07
    angent
    0.07
    ä»ĺãģij
    0.07
    æ¶Ľ
    0.07
     Gda
    0.07
    Activations Density 0.008%

    No Known Activations