© 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. 23873
    Prev
    Next
    INDEX
    Explanations

    quote prompts

    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
    èĢģ夫
    -0.07
    วà¸Ļ
    -0.06
     Boo
    -0.06
     Simmons
    -0.06
    ä¸ĬåĬł
    -0.06
    ä¸Ĭ身
    -0.06
    agu
    -0.06
    æĭĸ
    -0.06
    æĸ½
    -0.06
    éd
    -0.06
    POSITIVE LOGITS
    adero
    0.08
    æĶ¶ç©«
    0.08
    ostat
    0.08
    urez
    0.07
    ENZA
    0.07
    arit
    0.07
    -ser
    0.07
    ecchio
    0.07
     Äijúc
    0.07
    usher
    0.07
    Activations Density 0.226%

    No Known Activations