© 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. 20533
    Prev
    Next
    INDEX
    Explanations

    rotating and rotation

    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
    jenigen
    -0.10
    edig
    -0.08
    ICATION
    -0.08
    çĻ¾æĪĺ
    -0.08
    erton
    -0.08
    hood
    -0.08
    dling
    -0.07
    itter
    -0.07
    ergen
    -0.07
    owing
    -0.07
    POSITIVE LOGITS
    terdam
    0.10
    æľ¨é©¬
    0.09
    åĻ¨çļĦ
    0.08
    ally
    0.08
    ornado
    0.08
    ä¸Ģ转
    0.08
    ä¸Ģæĥ³
    0.08
    angles
    0.07
    äºĨä¸ĢåľĪ
    0.07
    icch
    0.07
    Activations Density 0.029%

    No Known Activations