© 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. 28935
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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
    —which
    -0.06
    —including
    -0.06
    ä¸ĢèĪ¬
    -0.06
    odo
    -0.06
     stiff
    -0.06
    —who
    -0.06
    rench
    -0.06
    —the
    -0.06
    çļĦæŶåĢĻåı¯ä»¥
    -0.06
    çļĦä¸ĢèĪ¬
    -0.06
    POSITIVE LOGITS
    ÅĽ
    0.08
    adona
    0.08
    chow
    0.08
    katan
    0.07
    spath
    0.07
    adients
    0.07
    ä¸įè¯Ĩ
    0.07
    epy
    0.07
    avax
    0.07
    èĥ
    0.07
    Activations Density 0.008%

    No Known Activations