© 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. 64028
    Prev
    Next
    INDEX
    Explanations

    connectors and additive terms

    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
    argas
    -0.07
    :not
    -0.07
    èĢĮæľª
    -0.07
    astas
    -0.07
    essar
    -0.07
    æ±IJ
    -0.07
    èĸ°
    -0.07
    filesize
    -0.07
    èIJ¨æĸ¯
    -0.07
    请ä¸ĭè½½
    -0.07
    POSITIVE LOGITS
     optionally
    0.11
     possibly
    0.11
     importantly
    0.10
     maybe
    0.09
     perhaps
    0.08
    çĶ±æѤ
    0.08
     Possibly
    0.08
    é¡į
    0.08
     presumably
    0.08
    æľīä¸ĢäºĽ
    0.08
    Activations Density 0.071%

    No Known Activations