© 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. 48721
    Prev
    Next
    INDEX
    Explanations

    materials or finishes

    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
    æķ£æŃ¥
    -0.10
    壮è§Ĥ
    -0.10
    åIJĥåĪ°
    -0.09
    unger
    -0.09
    èĦį
    -0.09
    楹
    -0.09
    级åĪ«çļĦ
    -0.09
    å¿ĺäºĨ
    -0.09
    NodeType
    -0.08
     McGregor
    -0.08
    POSITIVE LOGITS
    éĢı
    0.12
     surface
    0.11
    表éĿ¢
    0.11
     Surface
    0.10
    åīĸ
    0.09
    å¤Ķ
    0.09
    surface
    0.09
    ä¸įå¼Ģ
    0.09
    åĪº
    0.09
    bedo
    0.09
    Activations Density 0.119%

    No Known Activations