© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    already

    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
    ãĥ¬ãĥ«
    -0.08
    ÉĻrÉĻ
    -0.08
    _supported
    -0.08
    áĢĶáĢºáĢ¸
    -0.07
    umpang
    -0.07
     пÑĥзÑĭÑĢÑı
    -0.07
    /validation
    -0.07
    igny
    -0.07
    urray
    -0.07
    ä¹°åįķ
    -0.07
    POSITIVE LOGITS
     already
    0.16
    å·²æľīçļĦ
    0.15
    already
    0.14
    å·²æľī
    0.13
     déjÃł
    0.13
    å·²ç»ıæľī
    0.13
    Already
    0.13
    å·²ç»ıæĺ¯
    0.13
    å·²ç»ıå¾Ī
    0.13
     Already
    0.12
    Activations Density 0.352%

    No Known Activations