© 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. 32267
    Prev
    Next
    INDEX
    Explanations

    code 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
    ÑĤÑĥÑĢ
    -0.07
    没æľīå¿ħè¦ģ
    -0.07
    uck
    -0.07
    客
    -0.07
    è´©
    -0.06
     vertra
    -0.06
    ucked
    -0.06
    çļĦåIJĦç§į
    -0.06
    con
    -0.06
    éĥ¨ä½įçļĦ
    -0.06
    POSITIVE LOGITS
    å·§
    0.07
    ewnÄħ
    0.07
    å°ı家
    0.07
    ùn
    0.07
    çĥģ
    0.07
    ÑĢÑĸн
    0.06
    åĪ©çī©
    0.06
    ByKey
    0.06
    asts
    0.06
    /fast
    0.06
    Activations Density 0.013%

    No Known Activations