© 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. 40557
    Prev
    Next
    INDEX
    Explanations

    by [name]

    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
    باÙĨ
    -0.08
    hoven
    -0.08
    ouer
    -0.08
    celet
    -0.07
    enor
    -0.07
    åĵī
    -0.07
    UserProfile
    -0.07
     GruÃŁ
    -0.07
    lehem
    -0.07
    eneur
    -0.06
    POSITIVE LOGITS
     autoria
    0.08
    aku
    0.07
    æŀģåĵģ
    0.07
    ights
    0.07
     BEST
    0.07
    è·¯ä¸Ĭ
    0.06
    ures
    0.06
    ä½ļåIJį
    0.06
     dess
    0.06
    ึ
    0.06
    Activations Density 0.565%

    No Known Activations