© 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. 39329
    Prev
    Next
    INDEX
    Explanations

    acid rain

    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
    åļı
    -0.07
    UGIN
    -0.06
    èĢģ人家
    -0.06
    Ø¡
    -0.06
    ominator
    -0.06
    çį
    -0.06
    -0.06
    -ignore
    -0.06
    ç½·
    -0.06
    gress
    -0.06
    POSITIVE LOGITS
    ä¼Ļ伴们
    0.08
    dana
    0.08
    ارش
    0.08
    åħ°å¾·
    0.07
    æĹłä¸Ģ
    0.07
    tero
    0.07
    ogar
    0.07
     vera
    0.07
    æĪijå¼Ģå§ĭ
    0.07
    åħ°åį¡
    0.07
    Activations Density 0.807%

    No Known Activations