© 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. 14166
    Prev
    Next
    INDEX
    Explanations

    ticket, units, cost

    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
    nek
    -0.06
     Thin
    -0.06
    _wire
    -0.06
     Slave
    -0.06
    iloc
    -0.06
    å®´
    -0.06
    wij
    -0.06
     thin
    -0.06
    æ¼Ĥ
    -0.06
    èĸĦ
    -0.06
    POSITIVE LOGITS
    enger
    0.09
    trom
    0.09
    çģµæ´»
    0.08
    éķ¿èĢħ
    0.07
    çģµæ´»æĢ§
    0.07
    çģµæ´»çļĦ
    0.07
    intptr
    0.07
    éķ·èĢħ
    0.07
    onne
    0.07
     trom
    0.07
    Activations Density 0.006%

    No Known Activations