© 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. 50963
    Prev
    Next
    INDEX
    Explanations

    he or she / his or her

    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
    -anchor
    -0.09
    转载æĪĸå¼ķçĶ¨
    -0.08
    illas
    -0.07
    'order
    -0.07
    ulu
    -0.07
    assion
    -0.07
    arrant
    -0.07
     certes
    -0.07
    /Foundation
    -0.07
    били
    -0.07
    POSITIVE LOGITS
    çİ¥
    0.08
    ividual
    0.07
    eka
    0.06
    дие
    0.06
    ible
    0.06
    ahn
    0.06
    erator
    0.06
    isel
    0.06
    ione
    0.06
    æŁ¯è¾¾
    0.06
    Activations Density 0.052%

    No Known Activations