© 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. 51328
    Prev
    Next
    INDEX
    Explanations

    multi-function

    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
    itori
    -0.08
     flott
    -0.07
    ubar
    -0.07
    èĵ¦
    -0.07
    èݱæĸ¯
    -0.07
    éŨåīį
    -0.07
    æ¯Ķè¾ĥ容æĺĵ
    -0.06
    使çĶ¨éģĵåħ·
    -0.06
    quip
    -0.06
    зд
    -0.06
    POSITIVE LOGITS
    åħ¼
    0.23
    åħ¼åħ·
    0.21
    åħ¼ãģŃ
    0.18
    åħ¼ä»»
    0.18
    åIJĮæĹ¶è¿Ľè¡Į
    0.17
    åħ¼é¡¾
    0.17
     simultaneously
    0.17
     zugleich
    0.17
    æĹ¢æĺ¯
    0.16
     одновÑĢеменно
    0.16
    Activations Density 0.380%

    No Known Activations