© 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. 47103
    Prev
    Next
    INDEX
    Explanations

    making choices

    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
    èĩªå¤§
    -0.07
    æĺĨ
    -0.07
    ipe
    -0.07
    èĮ¹
    -0.07
    arbe
    -0.06
    ipes
    -0.06
    cken
    -0.06
     despite
    -0.06
    ahoo
    -0.06
    _mapped
    -0.06
    POSITIVE LOGITS
    æĬīæĭ©
    0.18
    åĨ³å®ļæĺ¯åIJ¦
    0.17
    åı¯ä»¥éĢīæĭ©
    0.17
    åı¯éĢīæĭ©
    0.17
     Choices
    0.16
     choices
    0.16
    Choices
    0.16
    choices
    0.16
     deciding
    0.15
    åı¯ä»¥éģ¸æĵĩ
    0.15
    Activations Density 0.417%

    No Known Activations