© 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. 50953
    Prev
    Next
    INDEX
    Explanations

    India, Atlanta, AIDS, ants, almonds

    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
    cience
    -0.08
    åħ®
    -0.08
    riad
    -0.08
    undle
    -0.07
    è¿ĺæĺ¯åľ¨
    -0.07
    åįĹåĽ½
    -0.07
    aan
    -0.07
     standa
    -0.07
    ä¸įæķ£
    -0.07
    è¿ĺæĺ¯ä¸Ģ
    -0.07
    POSITIVE LOGITS
    以åıĬä¸ĢäºĽ
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    éĶŃ
    0.08
    åıĬéĥ¨åĪĨ
    0.08
    åıĬåIJĦç§į
    0.08
    à¥ĥत
    0.07
     fall
    0.07
    为代表
    0.07
     Falls
    0.07
    ERVED
    0.07
    Activations Density 0.083%

    No Known Activations