© 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. 29519
    Prev
    Next
    INDEX
    Explanations

    magnetization, polarization, moments

    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
    utton
    -0.07
    erge
    -0.07
    ĥĿ
    -0.07
    ftype
    -0.06
    į°
    -0.06
    imal
    -0.06
    åįļæĸĩ
    -0.06
    æįī
    -0.06
    åĪ¶çīĪ
    -0.06
     ing
    -0.06
    POSITIVE LOGITS
    çŁ¢éĩı
    0.10
    ηγ
    0.08
    èĥŀ
    0.08
     vector
    0.08
    åIJijæĹ¥
    0.07
    cap
    0.07
    çŁ¢
    0.07
    vect
    0.07
    iba
    0.07
    éĩı
    0.07
    Activations Density 0.006%

    No Known Activations