© 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. 28363
    Prev
    Next
    INDEX
    Explanations

    closure or trace amines

    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
    cing
    -0.08
    swire
    -0.07
    fram
    -0.07
    å¸ĮæľĽå¯¹æĤ¨
    -0.07
    shore
    -0.07
    dessen
    -0.07
    壮æĹıèĩªæ²»åĮº
    -0.07
    ãĥ¼ãĤ«ãĥ¼
    -0.07
    sWith
    -0.07
    ths
    -0.07
    POSITIVE LOGITS
    less
    0.14
    edback
    0.09
    lessness
    0.09
    ×ķ
    0.08
    о
    0.08
    Ùĭ
    0.08
    urs
    0.08
    ful
    0.08
    able
    0.08
    ugh
    0.08
    Activations Density 0.005%

    No Known Activations