© 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. 39573
    Prev
    Next
    INDEX
    Explanations

    confiscation, censorship, inferior, plagiarized

    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
    adh
    -0.10
    oron
    -0.10
    иÑĢовки
    -0.09
    иÑĢовка
    -0.09
    poses
    -0.09
    éĥ¨ç½²
    -0.09
    è¦ĨçĽĸçİĩ
    -0.09
    astreet
    -0.08
    гад
    -0.08
    sis
    -0.08
    POSITIVE LOGITS
    ably
    0.12
    ously
    0.12
    ous
    0.11
    æĢ§çļĦ
    0.10
    èı¡
    0.10
    åŀł
    0.09
    ively
    0.09
    æĢ§çĸ¾çĹħ
    0.09
    åħ®
    0.09
    çľŃ
    0.09
    Activations Density 0.006%

    No Known Activations