© 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. 48086
    Prev
    Next
    INDEX
    Explanations

    movie and book titles

    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
    å°ijåĦ¿
    -0.11
    åħ¨å®¶
    -0.10
     substant
    -0.09
    onga
    -0.09
     ramp
    -0.09
    æıŃ
    -0.09
    å°º
    -0.09
    åĦ¿ç«¥
    -0.09
    èĪįä¸įå¾Ĺ
    -0.09
    æĪ¢
    -0.09
    POSITIVE LOGITS
    STA
    0.09
    rom
    0.08
    olas
    0.08
    âľĪ
    0.08
    ilog
    0.08
     ÑĢоман
    0.08
    éĤ¦
    0.08
    æµģåĬ¨
    0.08
    浪漫
    0.08
     rom
    0.08
    Activations Density 0.039%

    No Known Activations