© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52472
    Prev
    Next
    INDEX
    Explanations

    lamellar / lamotrigine / lamellar / lamellar / lam / lam / lamellar

    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
    åĩ¿
    -0.10
    èĥ½åĬĽå¼º
    -0.09
    amb
    -0.09
    verte
    -0.09
    ready
    -0.09
    toa
    -0.08
    Õ²
    -0.08
    оÑĢо
    -0.08
    ivism
    -0.08
    ย
    -0.08
    POSITIVE LOGITS
    à¹Ĩ
    0.11
    æĹłåĬĽ
    0.11
    est
    0.11
    ä¸İåIJ¦
    0.10
    sters
    0.09
    -hearted
    0.09
     à¹Ĩ
    0.09
    alysis
    0.09
    ç§ĥ
    0.09
    ä¸įåłª
    0.09
    Activations Density 0.002%

    No Known Activations