© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12086
    Prev
    Next
    INDEX
    Explanations

    neural crest, ectoderm, epithelia-derived

    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
    atha
    -0.08
    ä¸įæ±Ĥ
    -0.08
    atte
    -0.07
    å¤į审
    -0.07
    积åİĭ
    -0.07
    çīĪ
    -0.07
     ters
    -0.07
    DataBase
    -0.06
     Circuit
    -0.06
     Walters
    -0.06
    POSITIVE LOGITS
    ä¸Ģéĥ¨åĪĨ
    0.08
    -derived
    0.08
    zeug
    0.08
    è³
    0.07
    æĹ¥åIJİ
    0.07
     destined
    0.07
    future
    0.07
    åħ¨éĥ¨çļĦ
    0.07
     formed
    0.07
     later
    0.07
    Activations Density 0.072%

    No Known Activations