© 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. 32278
    Prev
    Next
    INDEX
    Explanations

    air bubble towards 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
    erce
    -0.08
    پرداز
    -0.07
    onta
    -0.07
     ê°Ģê³µ
    -0.07
     Input
    -0.07
    .vars
    -0.07
    解åĨ»
    -0.07
    anser
    -0.07
    varo
    -0.07
    שר
    -0.07
    POSITIVE LOGITS
     underwater
    0.08
    aphrag
    0.08
     method
    0.08
    å°ģ
    0.08
    æį¢æ°Ķ
    0.08
     vide
    0.07
    è£ĺ
    0.07
     contaminated
    0.07
    å¯ĨéĹŃ
    0.07
    éĩijé±¼
    0.07
    Activations Density 0.002%

    No Known Activations