© 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. 27921
    Prev
    Next
    INDEX
    Explanations

    rotation and related movements

    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
    éĻħ
    -0.07
    åIJijéĺ³
    -0.07
    ité
    -0.07
    æī¬
    -0.07
    plex
    -0.07
    ched
    -0.07
    æĿĥ人
    -0.07
    Indented
    -0.07
    .inst
    -0.07
    ayed
    -0.07
    POSITIVE LOGITS
     rotation
    0.10
     rotations
    0.10
    æĹĭ转
    0.09
     rotational
    0.09
    Rotation
    0.08
     Rotation
    0.08
    .rotate
    0.08
    rotation
    0.08
    (rotation
    0.07
     rotating
    0.07
    Activations Density 0.001%

    No Known Activations