© 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. 28896
    Prev
    Next
    INDEX
    Explanations

    rotation, alternation, and succession

    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
    wes
    -0.08
    éŀłèº¬
    -0.08
    apiro
    -0.07
     Prem
    -0.07
    æ¯ĶæĻ®éĢļ
    -0.07
    ÑĢÑģкого
    -0.07
    andles
    -0.07
    arie
    -0.07
    esso
    -0.07
    prem
    -0.07
    POSITIVE LOGITS
    è½®æµģ
    0.18
    è½®æį¢
    0.17
    äº¤æĽ¿
    0.17
     altern
    0.14
    è½®çķª
    0.13
     alternating
    0.13
     rotation
    0.12
    altern
    0.12
     rotate
    0.12
    è½®
    0.11
    Activations Density 0.162%

    No Known Activations