© 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. 54426
    Prev
    Next
    INDEX
    Explanations

    glands

    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
    tics
    -0.10
    ardu
    -0.10
    beck
    -0.10
    è´µ
    -0.10
    人为
    -0.09
    &D
    -0.09
    ture
    -0.09
     ÑĢеÑģÑĤ
    -0.09
    Stroke
    -0.09
    steller
    -0.09
    POSITIVE LOGITS
    located
    0.09
    èľĥ
    0.09
     glands
    0.09
     gland
    0.09
    oss
    0.08
    èģĬ
    0.08
    ç³Ĭæ¶Ĥ
    0.08
     Chapman
    0.08
    å£ģ
    0.08
    çĥĻ
    0.08
    Activations Density 0.345%

    No Known Activations