© 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. 26941
    Prev
    Next
    INDEX
    Explanations

    xml closing tags and attributes

    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
     somehow
    -0.07
    éĢıå½»
    -0.07
    ...',
    -0.07
    è§ģæѤ
    -0.06
    heten
    -0.06
    åľ¨è¿Ļä¸Ģ
    -0.06
    ixture
    -0.06
    [[
    -0.06
    /?
    -0.06
    eza
    -0.06
    POSITIVE LOGITS
    }while
    0.07
    (mut
    0.07
    pil
    0.07
    adays
    0.07
    ameni
    0.07
    ddb
    0.07
    çĴ¨
    0.07
    æĹ¥ä»¥
    0.07
    å¿ħ须注æĺİ
    0.07
    ="(
    0.07
    Activations Density 0.045%

    No Known Activations