© 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. 7923
    Prev
    Next
    INDEX
    Explanations

    questions starting with "I" or "Does"

    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
    ugu
    -0.07
    è¾ħ
    -0.07
    éĿŀ常好
    -0.07
    inqu
    -0.07
    çļĦä¸Ģå®ļ
    -0.06
    használ
    -0.06
    çļĦ天çĦ¶
    -0.06
     assumed
    -0.06
    une
    -0.06
    Neill
    -0.06
    POSITIVE LOGITS
    身临åħ¶å¢ĥ
    0.08
    çīį
    0.07
    ieten
    0.07
    ç§į
    0.07
    .down
    0.07
    éĥ½ä¸įæķ¢
    0.07
    å¤ļè¾¾
    0.07
    chip
    0.07
     Cheney
    0.06
    çĻ½ç¾Ĭ
    0.06
    Activations Density 0.009%

    No Known Activations