© 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. 26124
    Prev
    Next
    INDEX
    Explanations

    rotating

    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
    dden
    -0.08
    ollo
    -0.08
    çĪ±å²Ĺ
    -0.08
    è¾¾åħĭ
    -0.08
    punt
    -0.07
    ozilla
    -0.07
    åħĪæĿ¥
    -0.07
    éĢļåĭ¤
    -0.07
    Slash
    -0.07
     punt
    -0.07
    POSITIVE LOGITS
     rotating
    0.11
    æĹĭ转
    0.11
     rotate
    0.11
    æĹĭ
    0.10
     rotated
    0.10
    Rot
    0.09
     rotates
    0.09
     rotations
    0.09
    .rotate
    0.09
     Rotate
    0.09
    Activations Density 0.001%

    No Known Activations