© 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. 57522
    Prev
    Next
    INDEX
    Explanations

    listing separators and code symbols

    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
    terer
    -0.09
    tering
    -0.07
     Attention
    -0.07
    _framework
    -0.07
    жек
    -0.07
    zed
    -0.07
    ilan
    -0.07
    ter
    -0.07
    sher
    -0.06
    omag
    -0.06
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.08
    éķ°
    0.08
    .filters
    0.08
     половинÑĭ
    0.07
    udent
    0.07
     Bail
    0.07
    çľīå±±
    0.07
    ernel
    0.07
    å¨ħ
    0.07
    æĨĭ
    0.07
    Activations Density 0.004%

    No Known Activations