© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16826
    Prev
    Next
    INDEX
    Explanations

    small animal

    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
    Negative Logits
    è¯İ
    -0.09
    æŬ
    -0.09
     sink
    -0.09
    ivist
    -0.09
    enie
    -0.09
     ÑĦа
    -0.09
    оÑģÑĤей
    -0.08
    åįķ纯çļĦ
    -0.08
    å¾ĹæĦı
    -0.08
     Wong
    -0.08
    POSITIVE LOGITS
    å¦Ĥä»Ĭ
    0.09
     Parade
    0.09
    åĬŁå¤«
    0.09
    è¦ģåģļ好
    0.08
     beach
    0.08
    bound
    0.08
    èľļ
    0.08
    beth
    0.08
    èĢķ
    0.08
     Carrier
    0.08
    Activations Density 0.002%

    No Known Activations