© 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. 21114
    Prev
    Next
    INDEX
    Explanations

    pixel components and properties

    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
    holds
    -0.08
    éĻIJäºİ
    -0.07
    manship
    -0.07
    Ñĩего
    -0.07
    landet
    -0.07
    estr
    -0.07
    imers
    -0.07
    schild
    -0.07
    est
    -0.07
    äºİå¿ĥ
    -0.07
    POSITIVE LOGITS
    wise
    0.09
    ized
    0.09
    /column
    0.08
    weise
    0.08
     thÆ°á»Ľc
    0.08
    aceous
    0.08
    ÑĩиÑĤа
    0.08
    idia
    0.07
    icious
    0.07
    -wise
    0.07
    Activations Density 0.009%

    No Known Activations