© 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. 32510
    Prev
    Next
    INDEX
    Explanations

    project and report

    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
    ä¸Ģäºĭ
    -0.07
    为èį£
    -0.07
    ari
    -0.07
    odar
    -0.07
    ov
    -0.07
    eti
    -0.07
    ori
    -0.06
    iri
    -0.06
     Bog
    -0.06
    åľ¨ä¸ĸ
    -0.06
    POSITIVE LOGITS
    elay
    0.08
    emper
    0.07
    .erb
    0.07
    niu
    0.07
    nio
    0.07
    çľĭ好
    0.07
    ullet
    0.07
     salv
    0.07
    olgen
    0.06
    çİĭå¿Ĺ
    0.06
    Activations Density 0.277%

    No Known Activations