© 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. 16553
    Prev
    Next
    INDEX
    Explanations

    embryonic development

    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
    oned
    -0.11
    lify
    -0.10
     thiá»ĥu
    -0.09
    åij¨å¹´
    -0.09
    ened
    -0.09
    ç»Ī身
    -0.09
    leck
    -0.09
    ayed
    -0.09
    enance
    -0.08
    zza
    -0.08
    POSITIVE LOGITS
     же
    0.10
    ual
    0.09
    媳
    0.09
    доб
    0.09
    atic
    0.08
    evil
    0.08
    åĴ«
    0.08
    ØŃتاج
    0.08
    ÙĬÙĥ
    0.08
    ilio
    0.08
    Activations Density 0.021%

    No Known Activations