© 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. 56316
    Prev
    Next
    INDEX
    Explanations

    author biographies, history, botany

    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
     reigning
    -0.07
    ä¹ĭæķ°
    -0.07
    azer
    -0.07
     REGISTR
    -0.07
    UNKNOWN
    -0.07
    å°´å°¬
    -0.06
     lourd
    -0.06
    åı¯æĢľ
    -0.06
    ergus
    -0.06
    äºİæѤ
    -0.06
    POSITIVE LOGITS
    éĥ½æĺ¯èĩªå·±
    0.08
    以èĩªå·±
    0.08
    å°±æĺ¯ä»ĸ
    0.08
    بÙĥ
    0.07
     seines
    0.07
    otron
    0.07
    èijĹæľī
    0.07
    é¢ĩåħ·
    0.07
     co
    0.07
     luáºŃn
    0.07
    Activations Density 0.621%

    No Known Activations