© 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. 33483
    Prev
    Next
    INDEX
    Explanations

    random strings and code placeholders

    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
    æĸ°éĥ½
    -0.08
    à¸ŀร
    -0.08
    ushima
    -0.08
    à¸ij
    -0.08
    hoven
    -0.08
    klin
    -0.08
    iciel
    -0.08
    ÙIJÙĬÙİ
    -0.08
    åĩºäºİä¼łéĢĴæĽ´å¤ļä¿¡æģ¯ä¹ĭ缮çļĦ
    -0.08
    ÅĽcie
    -0.08
    POSITIVE LOGITS
    Lorem
    0.08
    azing
    0.07
     halluc
    0.06
    .getBytes
    0.06
    onaut
    0.06
    çĦ°
    0.06
    éķ¿å®ī
    0.06
    æѤç§į
    0.06
    好ãģį
    0.06
    æ¼Ķ示
    0.06
    Activations Density 0.269%

    No Known Activations