© 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. 19671
    Prev
    Next
    INDEX
    Explanations

    audio signal processing

    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
    éķľå¤´éĩĮ
    -0.11
     photographic
    -0.07
     foto
    -0.07
     Foto
    -0.06
     Turnbull
    -0.06
     Photographer
    -0.06
    åħīä¼ı
    -0.06
    æĶĿ影師
    -0.06
    车æŀ¶
    -0.06
    çľĭåĩº
    -0.06
    POSITIVE LOGITS
    å£°éŁ³
    0.13
    (sound
    0.13
    åIJ¬è§ī
    0.13
     recordings
    0.12
     louder
    0.12
    éŁ³éĩı
    0.12
    éĻįåĻª
    0.12
     sounds
    0.12
     sound
    0.12
     headphones
    0.12
    Activations Density 0.204%

    No Known Activations