© 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. 12435
    Prev
    Next
    INDEX
    Explanations

    electrolysis of water

    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
    管çIJĨåѦéĻ¢
    -0.08
     Scatter
    -0.07
    /manage
    -0.07
    è¡¥ä¸ģ
    -0.07
    æĺŁæłĩ
    -0.07
    管çIJĨåѦ
    -0.07
    /Register
    -0.07
    /Math
    -0.07
    -NLS
    -0.07
    رخ
    -0.07
    POSITIVE LOGITS
    çĶµè§£
    0.10
     electroly
    0.08
    áĥ¬áĥ§
    0.07
    è¹Ħ
    0.07
    éĤij
    0.07
    çĶµè§£è´¨
    0.07
    èªĵ
    0.07
     Cu
    0.07
    çĶµæŀģ
    0.07
    æĶ¾çĶµ
    0.06
    Activations Density 0.002%

    No Known Activations