© 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. 8286
    Prev
    Next
    INDEX
    Explanations

    selection and choice

    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
    hini
    -0.08
    labs
    -0.08
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    -0.07
    uits
    -0.07
    igare
    -0.07
    otine
    -0.07
    æķ°æį®ç»Łè®¡
    -0.07
    ats
    -0.07
    ModelState
    -0.07
    æĺ¯æĢİæł·çļĦ
    -0.07
    POSITIVE LOGITS
    éĢīæĭ©çļĦ
    0.17
    éĢīæĭ©
    0.15
     choice
    0.15
     selection
    0.15
    éĢīæĭ©ä¸į
    0.14
    çļĦéĢīæĭ©
    0.13
     lá»±a
    0.13
     choices
    0.13
    éĢīçĶ¨
    0.13
     selecting
    0.13
    Activations Density 0.233%

    No Known Activations