© 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. 15447
    Prev
    Next
    INDEX
    Explanations

    amplification, genes, terminals, resources, dentistry, force, animal

    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
    ynd
    -0.07
    la
    -0.06
     "
    -0.06
    _kwargs
    -0.05
    缸åħ³æݨèįIJ
    -0.05
    2
    -0.05
     '
    -0.05
    .
    -0.05
     form
    -0.05
    --
    -0.05
    POSITIVE LOGITS
    ļ
    0.09
    ussen
    0.09
    ichen
    0.09
    odelist
    0.08
    $j
    0.08
    ampo
    0.08
    (Spring
    0.08
    åįļä¼ļ
    0.08
    rekli
    0.08
    à¸Ħาย
    0.08
    Activations Density 0.055%

    No Known Activations