© 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. 12268
    Prev
    Next
    INDEX
    Explanations

    shuffle, mix, and stir

    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
    çķıæĥ§
    -0.09
    人æķ°
    -0.09
     optics
    -0.09
    ãĥ¡ãĥ³ãĥĪ
    -0.09
    ÑħоÑĤ
    -0.09
    áticas
    -0.08
    äºİæĺ¯æĪij
    -0.08
    rstrip
    -0.08
    _CLEAN
    -0.08
    çĨĻ
    -0.08
    POSITIVE LOGITS
    æIJħæĭĮ
    0.17
    æIJħ
    0.16
    åĮĢ
    0.13
     mixer
    0.11
    ä¸Ĭä¸ĭ
    0.11
    .shuffle
    0.10
     stirred
    0.10
     mixing
    0.10
     shuffle
    0.10
     Stir
    0.10
    Activations Density 0.044%

    No Known Activations