© 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. 16782
    Prev
    Next
    INDEX
    Explanations

    water splitting

    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
    æł¹æį®åĽ½å®¶
    -0.07
    sm
    -0.06
    ense
    -0.06
    åĽłä¸ºè¿ĻäºĽ
    -0.06
    alh
    -0.06
     cle
    -0.06
    åľ¨è¿Ľè¡Į
    -0.06
    åį³åľ¨
    -0.06
    arth
    -0.05
    è¶ħè¶ĬäºĨ
    -0.05
    POSITIVE LOGITS
    enix
    0.08
    eker
    0.08
     *))
    0.08
     Pubbl
    0.08
    ertos
    0.08
    (dispatch
    0.08
     вдÑĢÑĥг
    0.08
    ')['
    0.07
     suddenly
    0.07
    ä¸ºçĽ®çļĦ
    0.07
    Activations Density 0.033%

    No Known Activations