© 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. 26225
    Prev
    Next
    INDEX
    Explanations

    error checking :=

    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
    åºĶäºĪ
    -0.07
    ç¢
    -0.07
    zier
    -0.07
    bers
    -0.07
    atern
    -0.07
    éľĢ注æĦı
    -0.07
    ணà¯įà®Łà¯ģà®®à¯į
    -0.07
    à¥Īà¤Ĥ
    -0.07
    çļ¿
    -0.06
    åĴ½çĤİ
    -0.06
    POSITIVE LOGITS
    esian
    0.07
    ih
    0.07
    tera
    0.07
    cestor
    0.07
    lopen
    0.07
    çĦ¶
    0.07
     (::
    0.07
    ä¸ĩæĪ·
    0.06
    _predicate
    0.06
    æݨåĩº
    0.06
    Activations Density 0.039%

    No Known Activations