© 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. 21399
    Prev
    Next
    INDEX
    Explanations

    out or fails

    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
    ä¸ĭåIJĮ
    -0.08
    spflicht
    -0.08
    ))==
    -0.08
    å·²ç»ıæĬĬ
    -0.07
    次éĺħ读
    -0.07
    ä¼
    -0.07
    å°±å¤ŁäºĨ
    -0.07
    ernos
    -0.07
    å·²ç»ıå°Ĩ
    -0.07
    enaar
    -0.07
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀ
    0.10
    åıĬæŶ
    0.08
    æĢİä¹ĪåĬŀåij¢
    0.08
    è¾Ħ
    0.08
    ä¹ĭå¤Ħ
    0.08
    åĴĮéĹ®é¢ĺ
    0.08
    presso
    0.07
    ë©´
    0.07
    è¦ģåıĬæŶ
    0.07
    åºĶåıĬæŶ
    0.07
    Activations Density 0.080%

    No Known Activations