© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17214
    Prev
    Next
    INDEX
    Explanations

    for somewhere in fresh Python

    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
     ggf
    -0.08
    chner
    -0.08
    ä¹ĭçªĹ
    -0.08
    ellini
    -0.08
    yeong
    -0.07
    ç¯ĩä¸ī
    -0.07
    ulang
    -0.07
    мÑĥм
    -0.07
    авли
    -0.07
    cript
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.11
    æĸ°åĬłåĿ¡
    0.10
    ä¼ĹæīĢåij¨çŁ¥
    0.10
    åħ¢åħ¢ä¸ļä¸ļ
    0.10
    åĭĩå¾Ģ缴åīį
    0.09
    æ¯Ľæ³½ä¸ľ
    0.06
     ãĢĤ
    0.06
     sekä
    0.06
    0.06
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.06
    Activations Density 1.914%

    No Known Activations