© 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. 45487
    Prev
    Next
    INDEX
    Explanations

    challenges

    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
    ally
    -0.10
    ä¸ĢåĽŀäºĭ
    -0.09
    eln
    -0.08
    è¢ħè¢ħ
    -0.08
    ialized
    -0.08
    İ
    -0.07
    سÙĬس
    -0.07
    ational
    -0.07
    iger
    -0.07
    Å¡to
    -0.07
    POSITIVE LOGITS
    forder
    0.08
     posed
    0.08
     khÄĥn
    0.08
    iswa
    0.08
    ingly
    0.08
    bourg
    0.08
    eur
    0.08
    æĢ§åľ°
    0.07
    andra
    0.07
    бÑĢе
    0.07
    Activations Density 0.033%

    No Known Activations