© 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. 35610
    Prev
    Next
    INDEX
    Explanations

    transgressions, infractions, infringement

    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
    çĿ¬
    -0.12
    loud
    -0.11
    wards
    -0.09
    ä¸ĢéĹª
    -0.09
    ovel
    -0.09
    åĮħ袱
    -0.09
    ream
    -0.09
    æĢģ
    -0.09
    åīįéĢĶ
    -0.09
    æĹłç©·
    -0.08
    POSITIVE LOGITS
    spir
    0.09
    ean
    0.08
    ụ
    0.08
    éĢ¼è¿ij
    0.08
    uvw
    0.08
    ponent
    0.08
    EXEC
    0.08
    ä¸įåıĬ
    0.08
     Vict
    0.07
    iveness
    0.07
    Activations Density 0.013%

    No Known Activations