© 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. 14077
    Prev
    Next
    INDEX
    Explanations

    vacuum and suction

    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
    庸
    -0.07
    ješ
    -0.07
     cush
    -0.07
     collision
    -0.07
    æĪijè¡Į
    -0.07
     Collision
    -0.07
    ä¸İç»´æĬ¤
    -0.07
     thừa
    -0.07
    æĬĸ
    -0.07
    collision
    -0.07
    POSITIVE LOGITS
    è´Łåİĭ
    0.12
    æĭīåĪ°
    0.11
    pull
    0.10
    .pull
    0.10
     pulling
    0.10
     pull
    0.10
    æĭīåĬ¨
    0.10
     hút
    0.09
     pulls
    0.09
     Pull
    0.09
    Activations Density 0.053%

    No Known Activations