© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46506
    Prev
    Next
    INDEX
    Explanations

    code punctuation and fragments

    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
    ķĮ
    -0.07
    aranya
    -0.07
     helm
    -0.07
    æĬĬä¸Ģ个
    -0.07
    çĶļèĩ³è¿ĺæľī
    -0.07
    éĽĨç¾İ
    -0.07
    åĬĥ
    -0.06
     //~
    -0.06
    mut
    -0.06
    ilha
    -0.06
    POSITIVE LOGITS
    ailable
    0.07
    otts
    0.07
    宣
    0.07
    åIJĮ人
    0.07
    éĹº
    0.07
    á»ģ
    0.07
    ä¸ĢéĿ¢
    0.06
     licked
    0.06
    å»ĵ
    0.06
     maxValue
    0.06
    Activations Density 0.003%

    No Known Activations