© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14998
    Prev
    Next
    INDEX
    Explanations

    meet the or your

    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
    itize
    -0.09
    nement
    -0.09
    æĸ°åĬłåĿ¡
    -0.09
    jenigen
    -0.09
    ggia
    -0.09
    ities
    -0.08
    礴
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    ught
    -0.08
    aikan
    -0.08
    POSITIVE LOGITS
     gỡ
    0.13
    TING
    0.10
    ropolit
    0.09
    ting
    0.09
    ropolitan
    0.09
    ropolis
    0.09
    ings
    0.09
    ropole
    0.08
     mẻ
    0.08
    tings
    0.08
    Activations Density 0.045%

    No Known Activations