© 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. 29240
    Prev
    Next
    INDEX
    Explanations

    material, fuel, partner drug

    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
    太å¤ļçļĦ
    -0.08
    ä¸įæİĴéĻ¤
    -0.08
    ä¾¥
    -0.08
    äºĴåĬ¨äº¤æµģ
    -0.08
    å¾Īå¤ļçļĦ
    -0.08
    veli
    -0.08
    uruh
    -0.07
    itecture
    -0.07
    æĸ°çļĦä¸Ģ
    -0.07
    太å¤ļäºĨ
    -0.07
    POSITIVE LOGITS
    éĤ£äºĽ
    0.09
     olyan
    0.09
     highly
    0.09
    åIJ«æľī
    0.08
     non
    0.08
    åħ·æľī
    0.08
    æķı
    0.07
    æĺ¯åħ·æľī
    0.07
    ä»ĸ认为
    0.07
     something
    0.07
    Activations Density 0.347%

    No Known Activations