© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21139
    Prev
    Next
    INDEX
    Explanations

    omics and proteomic analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡Ķ
    -0.09
    jong
    -0.08
    éĽı
    -0.08
    spiel
    -0.08
    vak
    -0.08
     Mane
    -0.08
    uggy
    -0.08
     horns
    -0.08
    æŃ¥æŃ¥
    -0.08
    _packets
    -0.08
    POSITIVE LOGITS
    å¾ģä¿¡
    0.11
    omics
    0.10
    erah
    0.09
    Catalog
    0.09
    å®ĿèĹı
    0.09
    å¯Ħ
    0.09
    çŃł
    0.09
    åħħå®ŀ
    0.08
    个æĢ§åĮĸ
    0.08
    Atl
    0.08
    Activations Density 0.574%

    No Known Activations