© 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. 55862
    Prev
    Next
    INDEX
    Explanations

    but

    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
     Nues
    -0.09
    łĢ
    -0.09
     Ouver
    -0.09
     Teixe
    -0.09
    ephy
    -0.08
    æĬŀ
    -0.08
    viders
    -0.08
    Ãłnh
    -0.08
     Insg
    -0.08
    "struct
    -0.08
    POSITIVE LOGITS
    m
    0.08
    ity
    0.07
    age
    0.07
    H
    0.07
    s
    0.07
    t
    0.07
    ine
    0.06
    ation
    0.06
    Q
    0.06
    å¤ļå¹´çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations