© 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. 14482
    Prev
    Next
    INDEX
    Explanations

    technical file and user actions

    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
    æķ°æį®çºłéĶĻ
    -0.09
    ç½ijç«Ļ导èĪª
    -0.09
    .ipv
    -0.08
    CharacterSet
    -0.08
    /gcc
    -0.08
    HeaderCode
    -0.08
    borough
    -0.08
    /Instruction
    -0.08
    -minus
    -0.08
    REFIX
    -0.08
    POSITIVE LOGITS
     user
    0.07
     `
    0.07
    ¶
    0.07
     initialization
    0.06
     manual
    0.06
     manually
    0.06
     confusing
    0.06
    åIJĪ秣
    0.06
     inline
    0.06
    @@
    0.06
    Activations Density 1.285%

    No Known Activations