© 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. 23948
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    æŀ¶
    -0.10
    liner
    -0.09
    ÑıÑĤÑĮ
    -0.09
    ÑĮÑı
    -0.08
     Ùħد
    -0.08
    æŃĥ
    -0.08
    ãĥ¼ãĤº
    -0.08
    imentary
    -0.08
    ents
    -0.08
     WAV
    -0.08
    POSITIVE LOGITS
    åīįåĩłå¹´
    0.11
    åīįèĢħ
    0.11
    åīįåĩłå¤©
    0.09
    åīįä¸įä¹ħ
    0.09
    æĥ³èµ·æĿ¥
    0.08
    麸
    0.08
    0
    0.08
    派驻
    0.08
     *----------------------------------------------------------------
    0.07
    æĪ¬
    0.07
    Activations Density 0.200%

    No Known Activations