© 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. 8651
    Prev
    Next
    INDEX
    Explanations

    start of phrases or sequences

    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
    quê
    -0.10
    ité
    -0.10
    ição
    -0.09
    omio
    -0.09
    ieli
    -0.09
    iseur
    -0.09
    æĸ°èĢģ客æĪ·
    -0.09
    aston
    -0.09
    raries
    -0.09
    aster
    -0.08
    POSITIVE LOGITS
    schuss
    0.10
    egy
    0.10
    lings
    0.09
    ting
    0.08
    swith
    0.08
    OrUpdate
    0.08
    ewart
    0.08
    ingle
    0.08
    nings
    0.07
    ellite
    0.07
    Activations Density 0.072%

    No Known Activations