© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    rotation, symmetric tensor, su(2)

    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
    alap
    -0.08
    orado
    -0.07
    ÙĪتÙĬ
    -0.07
    sung
    -0.07
    alai
    -0.07
    ÙĪرÙĬ
    -0.07
    ORS
    -0.07
     staged
    -0.07
    Ñģло
    -0.07
    adet
    -0.06
    POSITIVE LOGITS
    æĹĭ转
    0.08
    rotate
    0.08
     rotational
    0.08
    ardini
    0.08
    转åĬ¨
    0.08
    rot
    0.07
    abend
    0.07
     Rot
    0.07
    Rotation
    0.07
    磩éĺµ
    0.07
    Activations Density 0.001%

    No Known Activations