© 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. 50376
    Prev
    Next
    INDEX
    Explanations

    motion with direction

    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
    oad
    -0.08
    stech
    -0.07
    çŃ
    -0.07
    æĪijäºĨ
    -0.07
    äºĨçļĦ
    -0.07
    ä¼łçļĦ
    -0.07
    جر
    -0.06
    полÑĮ
    -0.06
    她äºĨ
    -0.06
    ÑĤоÑĢÑĭ
    -0.06
    POSITIVE LOGITS
     into
    0.18
     Into
    0.13
    Into
    0.13
     INTO
    0.13
    .into
    0.13
    into
    0.12
     внÑĥÑĤÑĢÑĮ
    0.12
    _into
    0.11
    åħ¥
    0.11
     away
    0.11
    Activations Density 0.302%

    No Known Activations