© 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. 5130
    Prev
    Next
    INDEX
    Explanations

    protein and related biological terms

    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
    笪
    -0.10
    upe
    -0.10
    OrUpdate
    -0.09
    apid
    -0.09
    itters
    -0.09
    town
    -0.08
    æĹłäºº
    -0.08
    ä¸ĩçī©
    -0.08
    erah
    -0.08
    upt
    -0.08
    POSITIVE LOGITS
    aceous
    0.21
    èĥ¨
    0.11
    ì§Ī
    0.10
     kinase
    0.10
    質
    0.10
    èĶ»
    0.10
    EXIST
    0.09
    仪
    0.09
    ortho
    0.09
    ases
    0.09
    Activations Density 0.200%

    No Known Activations