© 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. 42380
    Prev
    Next
    INDEX
    Explanations

    better + comparison

    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
    ãĥĨãĤ£ãĥĥãĤ¯
    -0.10
    ubat
    -0.09
    并èĮĤ
    -0.09
    ़
    -0.09
    åĩıçģ¾
    -0.09
    ÙĬØ«
    -0.09
    sWith
    -0.09
    inality
    -0.09
    yclopedia
    -0.09
    大åIJĥ
    -0.09
    POSITIVE LOGITS
    -than
    0.17
     than
    0.14
    _than
    0.13
    than
    0.11
    _THAN
    0.10
    er
    0.10
    idge
    0.10
    u
    0.09
     suited
    0.09
    ed
    0.09
    Activations Density 0.021%

    No Known Activations