© 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. 17668
    Prev
    Next
    INDEX
    Explanations

    hmm or mmm interjections

    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
    Öģ
    -0.10
    yms
    -0.08
    chnik
    -0.08
    <|box_end|>
    -0.08
    addir
    -0.08
    /or
    -0.08
    otify
    -0.08
    ówe
    -0.08
    uards
    -0.08
    asley
    -0.08
    POSITIVE LOGITS
    åĬŀæ³ķ
    0.07
    ness
    0.06
    æľīçļĦ
    0.06
    omo
    0.06
    æľīçļĦåIJĮåѦ
    0.06
    .
    0.06
    ãģªãģĮãĤī
    0.06
    tima
    0.06
    ä¸įåĨ³
    0.06
    æŶåĢĻ
    0.06
    Activations Density 0.004%

    No Known Activations