© 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. 50291
    Prev
    Next
    INDEX
    Explanations

    million mile warranty

    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
    engi
    -0.08
    ritis
    -0.08
    è¾ĥå¤ļçļĦ
    -0.08
    ç´¢æĢ§
    -0.08
    好æŃ¹
    -0.08
    çĥŃæĴŃ
    -0.08
    æľīè¾ĥ大
    -0.07
    è¾ĥå¤ļ
    -0.07
    inton
    -0.07
    æľīä¸Ģçķª
    -0.07
    POSITIVE LOGITS
     tiny
    0.08
     incredibly
    0.08
     incredible
    0.08
    åĩłä¹İ没æľī
    0.08
    /tiny
    0.08
     unimagin
    0.08
     (!
    0.07
     vast
    0.07
     unparalleled
    0.07
     instantaneous
    0.07
    Activations Density 0.186%

    No Known Activations