© 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. 14881
    Prev
    Next
    INDEX
    Explanations

    menu item / option

    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
    ajer
    -0.07
    игÑĢа
    -0.07
    ç¿Ķ
    -0.07
     Betten
    -0.07
    illy
    -0.06
    رس
    -0.06
    icata
    -0.06
    ä¸ĩå¹´
    -0.06
    _lists
    -0.06
    åįĥ人
    -0.06
    POSITIVE LOGITS
     components
    0.12
     elements
    0.12
    ç»ĦæĪIJéĥ¨åĪĨ
    0.11
     items
    0.10
     pieces
    0.10
     segments
    0.10
    components
    0.10
    çīĩ段
    0.10
    éĥ¨ä»¶
    0.10
     particles
    0.09
    Activations Density 0.556%

    No Known Activations