© 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. 32379
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a noun

    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»åħĭ
    -0.09
    æī«
    -0.09
    CJK
    -0.09
    迤
    -0.09
    äºĭåĦ¿
    -0.09
    ÑģÑĤÑĢоен
    -0.09
    æľīä»»ä½ķ
    -0.09
    å¦ĤæѤ
    -0.08
    翱
    -0.08
    踩
    -0.08
    POSITIVE LOGITS
    ont
    0.09
    éĻ¢åī¯éĻ¢éķ¿
    0.08
    ssp
    0.08
     list
    0.08
    缸åºĶ
    0.08
    éķ¿éķ¿çļĦ
    0.08
    ãģ¦ãģĦ
    0.08
     SD
    0.08
    ents
    0.08
     disclaimer
    0.08
    Activations Density 0.392%

    No Known Activations