© 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. 65091
    Prev
    Next
    INDEX
    Explanations

    north, west, shrink, reduced, until

    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
     arguably
    -0.07
    为åĩĨ
    -0.07
    级
    -0.07
    λεί
    -0.06
    ä¸Ĭä¸ĭ
    -0.06
    ç®Ĺä¸įä¸Ĭ
    -0.06
    azz
    -0.06
    ugh
    -0.06
    ç´ļçļĦ
    -0.06
    ç´ļ
    -0.06
    POSITIVE LOGITS
    缴åĪ°
    0.23
     until
    0.23
    缴èĩ³
    0.22
    until
    0.21
    _until
    0.20
     Until
    0.18
    Until
    0.18
     hasta
    0.17
    ä¸Ģ缴åĪ°
    0.16
     jusqu
    0.16
    Activations Density 0.143%

    No Known Activations