© 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. 55803
    Prev
    Next
    INDEX
    Explanations

    lizard, RX, Wednesday

    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
     behold
    -0.07
    beh
    -0.07
    _lazy
    -0.07
    æķ´ä¸ªè¿ĩç¨ĭ
    -0.07
    (runtime
    -0.07
    碰
    -0.07
     unpl
    -0.07
    åĢ¼æѤ
    -0.07
    åĴĮ社ä¼ļåıijå±ķ
    -0.07
    Abr
    -0.07
    POSITIVE LOGITS
    éľĦ
    0.08
    ligh
    0.08
    ytte
    0.07
    opo
    0.07
    åIJĹ
    0.07
    èĬ¸
    0.07
     ts
    0.07
    å®ŀå¿ĥ
    0.06
    æĶ¶èĹı
    0.06
     cos
    0.06
    Activations Density 0.008%

    No Known Activations