© 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. 18869
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    âĢ¦âĢ¦ãĢĤ
    -0.12
    ...).
    -0.10
    âĢ¦,
    -0.10
    âĢ¦ãĢĤ
    -0.10
    ...,
    -0.09
     **«
    -0.09
    âĤ¬.
    -0.09
     âĤ¬.
    -0.09
    ÑģÑı
    -0.09
    âĢ¦).
    -0.09
    POSITIVE LOGITS
    **”
    0.09
     ?**
    0.08
    ÑĬл
    0.08
    \"
    0.08
    ()`
    0.08
    %**
    0.08
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    0.08
    âĪ½
    0.07
    ?**
    0.07
    ()"
    0.07
    Activations Density 0.005%

    No Known Activations