© 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. 57113
    Prev
    Next
    INDEX
    Explanations

    surface descriptions

    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
    ɦ
    -0.09
    agnol
    -0.09
    ä¹ŁæľīäºĽ
    -0.08
    è¿ĺæĺ¯æ²¡æľī
    -0.08
    ÑİÑĢ
    -0.08
    é£ŀé¾Ļ
    -0.08
    è¿ĺæĺ¯ä¸į
    -0.08
    ciel
    -0.08
    å¯Ĩæĸ¯
    -0.08
    igos
    -0.08
    POSITIVE LOGITS
    oc
    0.07
    å°Ķ
    0.06
     begr
    0.06
    ç¹ģ
    0.06
    uth
    0.06
    ot
    0.06
     mut
    0.06
    og
    0.06
    墨
    0.06
    åĨį
    0.05
    Activations Density 0.278%

    No Known Activations