© 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. 44072
    Prev
    Next
    INDEX
    Explanations

    exemption

    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
    ersist
    -0.09
    天å¤ĸ
    -0.09
    æľīå½¢
    -0.08
    éĢ¼è¿«
    -0.08
    å¿ħå¡«
    -0.08
    迫使
    -0.08
     compulsory
    -0.07
    紧迫æĦŁ
    -0.07
    еÑĢед
    -0.07
    ä¸įåı¯éģ¿åħįåľ°
    -0.07
    POSITIVE LOGITS
     exemption
    0.13
    åħį
    0.13
    åħįäºİ
    0.13
     exemptions
    0.13
    è±ģåħį
    0.13
     exempt
    0.12
    åħįéĻ¤
    0.11
    åħįç¨İ
    0.10
     exem
    0.10
     protections
    0.10
    Activations Density 0.091%

    No Known Activations