© 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. 15993
    Prev
    Next
    INDEX
    Explanations

    haploid, diploid

    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
    allo
    -0.09
    prite
    -0.08
    ocrin
    -0.08
    ICC
    -0.08
     najmniej
    -0.08
    .hasClass
    -0.07
    éķ¿åħ´
    -0.07
    cznie
    -0.07
    ousel
    -0.07
    ancements
    -0.07
    POSITIVE LOGITS
    èªĮ
    0.07
    åĪ¶çļĦ
    0.07
    Ļ
    0.07
    enf
    0.07
    eny
    0.06
    ity
    0.06
    Ïħ
    0.06
    ient
    0.06
    ify
    0.06
    icientes
    0.06
    Activations Density 0.003%

    No Known Activations