© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4912
    Prev
    Next
    INDEX
    Explanations

    molecular mechanisms

    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
    Negative Logits
    ä½Ĩä¸įéĻIJäºİ
    -0.13
    egers
    -0.10
    autiful
    -0.10
    ़
    -0.09
    imizer
    -0.09
    endom
    -0.09
    Ķ
    -0.09
    fulness
    -0.09
    ãĥ£
    -0.09
    raq
    -0.08
    POSITIVE LOGITS
    ly
    0.19
    ities
    0.14
    ized
    0.14
    о
    0.14
    ãĥ³
    0.13
    s
    0.13
    o
    0.13
    ات
    0.13
    mente
    0.12
    åĭĩå¾Ģ缴åīį
    0.11
    Activations Density 0.076%

    No Known Activations