© 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. 53615
    Prev
    Next
    INDEX
    Explanations

    support for

    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
    ary
    -0.09
    åĪĿãĤģãģ¦
    -0.09
    éģ´
    -0.09
    èµ·æŃ¥
    -0.09
    èĢĥ
    -0.08
    å°Ŀ
    -0.08
    ars
    -0.08
    èĥ¸
    -0.08
    dance
    -0.08
    igi
    -0.08
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.11
    æĹ©çĤ¹
    0.11
    å¼Ĥåľ°
    0.10
    å°½æĹ©
    0.10
    尽快
    0.10
    赶快
    0.10
    çļĦåģļæ³ķ
    0.10
    åĴĮæĶ¯æĮģ
    0.09
    èļĮ
    0.09
    @student
    0.09
    Activations Density 0.043%

    No Known Activations