© 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. 11653
    Prev
    Next
    INDEX
    Explanations

    apoplexy, cancer, treatment, government, anorexia

    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
    æĸ¯æĭī
    -0.08
    å¤ļèĬ¬
    -0.07
     undermin
    -0.07
    empel
    -0.07
    дени
    -0.07
    (logger
    -0.07
    æ½Ł
    -0.07
     Gö
    -0.07
    åķ¡
    -0.07
    åģļéĶĻ
    -0.07
    POSITIVE LOGITS
    æľīç¼ĺ
    0.08
    æľºçIJĨ
    0.08
    å¤ļè§ģäºİ
    0.08
    åıĪ称
    0.08
    åıĪåIJį
    0.07
    eté
    0.07
    è§ģäºİ
    0.07
    å¦ĩ人
    0.07
    éĢļ
    0.07
    çĹħç¨ĭ
    0.07
    Activations Density 0.012%

    No Known Activations