© 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. 29884
    Prev
    Next
    INDEX
    Explanations

    full license

    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
    ually
    -0.09
    zzo
    -0.09
    ally
    -0.09
    raphe
    -0.09
    zelfde
    -0.09
    hips
    -0.09
    pery
    -0.09
    ../
    -0.09
    bergen
    -0.09
    uken
    -0.09
    POSITIVE LOGITS
    ness
    0.13
    æĪĸéĥ¨åĪĨ
    0.10
    ings
    0.09
    -bodied
    0.09
    itude
    0.09
    eren
    0.08
    /full
    0.08
    à¹Ĩ
    0.08
    (er
    0.08
    ständig
    0.08
    Activations Density 0.036%

    No Known Activations