© 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. 1242
    Prev
    Next
    INDEX
    Explanations

    picking numbers and probabilities

    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
    iri
    -0.07
    Weekly
    -0.07
     chains
    -0.07
     Weekly
    -0.07
    olars
    -0.07
    vast
    -0.06
    olu
    -0.06
    ãĤªãĥª
    -0.06
    olar
    -0.06
    åĪ¤æĸŃ
    -0.06
    POSITIVE LOGITS
    ESIS
    0.09
    esis
    0.08
    trup
    0.08
    .fm
    0.08
    loat
    0.07
    åĵĴ
    0.07
    á»įng
    0.07
    (es
    0.07
    æĸ¤
    0.07
    ilent
    0.07
    Activations Density 0.002%

    No Known Activations