© 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. 10825
    Prev
    Next
    INDEX
    Explanations

    big followed by noun

    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
    vrier
    -0.10
    大åįĥ
    -0.10
    大åįĬ
    -0.09
    大åħ¸
    -0.09
    ToBounds
    -0.09
    edelta
    -0.09
    大殿
    -0.09
    大æĥĬ
    -0.09
    å¤§ä½ľæĪĺ
    -0.09
    ********************
    -0.09
    POSITIVE LOGITS
    à¹ĥà¸Ī
    0.08
    iose
    0.08
    ening
    0.08
    ç¨ĭ度ä¸Ĭ
    0.08
    å¹´å¤ľ
    0.08
     اÙĦشأÙĨ
    0.07
    -hearted
    0.07
     اÙĦسÙĨ
    0.07
    ened
    0.07
     mẽ
    0.07
    Activations Density 0.072%

    No Known Activations