© 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. 64907
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    ANO
    -0.07
    aval
    -0.06
     ↵↵
    -0.06
    terne
    -0.06
    interop
    -0.06
      ↵↵
    -0.06
    _PTR
    -0.06
    éĻ©
    -0.06
    زÙĩ
    -0.05
       ↵↵
    -0.05
    POSITIVE LOGITS
    <|box_end|>
    0.09
    uris
    0.09
    ¨
    0.08
    zerw
    0.08
    odash
    0.08
     Fabriz
    0.08
    åħ¶ä»ĸ人çļĦ
    0.08
    书ä¸ŃçļĦ
    0.08
    áĢ²áĢ·
    0.08
    ovol
    0.07
    Activations Density 0.347%

    No Known Activations