© 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. 15450
    Prev
    Next
    INDEX
    Explanations

    questioning exceptions or outcomes

    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
    etar
    -0.08
    èĩ¨
    -0.08
    surf
    -0.07
    è·¨
    -0.07
    ogan
    -0.07
    è·¨è¶Ĭ
    -0.07
    è¦ģ被
    -0.07
    临
    -0.07
    rides
    -0.07
    è¸ıæŃ¥
    -0.07
    POSITIVE LOGITS
    Occurred
    0.07
    çļĦåıįåºĶ
    0.07
     obvious
    0.07
    åıįåºĶ
    0.06
    æ²ĥæĸ¯
    0.06
    æĬĬ她
    0.06
    ypo
    0.06
    ×ķ
    0.06
    ç«ĭæĸ°
    0.06
    æĬĬä»ĸ
    0.06
    Activations Density 0.001%

    No Known Activations