© 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. 33956
    Prev
    Next
    INDEX
    Explanations

    TxB2, IgE, micrograms, schema, SV, New York

    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
    ember
    -0.07
    åģļä¸ĢäºĽ
    -0.07
    igo
    -0.07
    yal
    -0.07
    ock
    -0.07
    gon
    -0.07
    èĥ½åĬĽçļĦåŁ¹åħ»
    -0.06
    rene
    -0.06
    hra
    -0.06
    hares
    -0.06
    POSITIVE LOGITS
    æĪij羣
    0.08
    Õ®
    0.07
    ToUpdate
    0.07
    Unchecked
    0.07
    egot
    0.07
    ัà¸ĩà¸ģ
    0.07
    áĢĨ
    0.07
    UGC
    0.07
    ä¸ĢåłĤ
    0.07
    ุà¸Ķ
    0.06
    Activations Density 0.034%

    No Known Activations