© 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. 12784
    Prev
    Next
    INDEX
    Explanations

    selecting task before

    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
    enia
    -0.08
    æķ°æį®æĺ¾ç¤º
    -0.08
    顽
    -0.08
    สัà¸ĩà¹Ģà¸ģà¸ķ
    -0.08
    jala
    -0.07
    nish
    -0.07
    æĬ¥åijĬæĺ¾ç¤º
    -0.07
    继ç»Ńä¿ĿæĮģ
    -0.07
     erh
    -0.07
    hofer
    -0.07
    POSITIVE LOGITS
     determining
    0.12
    ç¡®å®ļ
    0.12
     decisions
    0.11
    è§ĦåĪĴ
    0.11
     planning
    0.11
    ç¡®å®ļäºĨ
    0.11
     decision
    0.11
    åĨ³å®ļ
    0.10
    åĨ³å®ļäºĨ
    0.10
     selecting
    0.10
    Activations Density 0.268%

    No Known Activations