© 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. 30127
    Prev
    Next
    INDEX
    Explanations

    software module and plugin components

    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
    queo
    -0.07
    åĴ¨
    -0.07
    leta
    -0.06
     scop
    -0.06
    merce
    -0.06
    ank
    -0.06
     $#
    -0.06
     captured
    -0.06
    #__
    -0.06
    alem
    -0.06
    POSITIVE LOGITS
    -provider
    0.09
    -generic
    0.08
    _generic
    0.08
    ihak
    0.08
    =default
    0.08
    _PROVID
    0.08
    ĥĿ
    0.08
    -contrib
    0.08
    ConverterFactory
    0.08
    éĢĤéħįåĻ¨
    0.08
    Activations Density 0.385%

    No Known Activations