© 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. 41681
    Prev
    Next
    INDEX
    Explanations

    dropdowns, selects, and comboboxes

    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
    allar
    -0.07
    æķijæĬ¤
    -0.07
    åĽ½å®Ŀ
    -0.07
    æĹĹèĪ°
    -0.07
     bytecode
    -0.07
    Stamp
    -0.07
     handleError
    -0.07
     tarp
    -0.07
    etri
    -0.06
    æĺİçģ«
    -0.06
    POSITIVE LOGITS
    choices
    0.11
     selections
    0.11
    /select
    0.11
     Choices
    0.11
     selection
    0.11
    Choices
    0.11
     choices
    0.11
    -selection
    0.10
    è¿Ľè¡ĮéĢīæĭ©
    0.10
    selection
    0.10
    Activations Density 0.335%

    No Known Activations