© 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. 45597
    Prev
    Next
    INDEX
    Explanations

    Earth, fire, Gemini, type

    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
    è¹Ń
    -0.07
    ograph
    -0.07
    åĹħ
    -0.07
    etro
    -0.06
    人æ°ijåħ±åĴĮåĽ½
    -0.06
    åħ·æľīå¾Īé«ĺçļĦ
    -0.06
    ä¸Ĭ人
    -0.06
    被æĬĵ
    -0.06
    éĺµé£İ
    -0.06
    ç¥ŀçĪ¶
    -0.06
    POSITIVE LOGITS
    å¼±çļĦ
    0.08
    cessive
    0.08
     weak
    0.08
    åħ³ç³»ä¸Ń
    0.08
    -mediated
    0.07
     weakened
    0.07
     Weak
    0.07
    åĩıå¼±
    0.07
    Weak
    0.07
     mediated
    0.07
    Activations Density 0.001%

    No Known Activations