© 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. 48032
    Prev
    Next
    INDEX
    Explanations

    replace with other values

    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
    TAIL
    -0.08
    çıį
    -0.08
    天边
    -0.08
    åĪģ
    -0.07
    åĢ¾åŁİ
    -0.07
    parameters
    -0.07
    èī°
    -0.07
    .parameters
    -0.07
    qd
    -0.07
     домÑĥ
    -0.07
    POSITIVE LOGITS
    å¡«
    0.09
    åĩ¡
    0.09
    æĽ¿æį¢
    0.09
     replace
    0.09
    å¡«åħħ
    0.09
    åĩ¡æĺ¯
    0.09
    FillColor
    0.08
     replacement
    0.08
     replacing
    0.08
    -fill
    0.08
    Activations Density 0.054%

    No Known Activations