© 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. 24327
    Prev
    Next
    INDEX
    Explanations

    citing reasons or evidence

    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
    åı¶åŃIJ
    -0.10
    ç¼Ł
    -0.10
    çĶ³è¯ī
    -0.10
    æľīæĦıä¹ī
    -0.10
    ä½łè§īå¾Ĺ
    -0.10
    ìľĪ
    -0.09
    磶
    -0.09
    麸
    -0.09
    reira
    -0.09
    们éĥ½
    -0.09
    POSITIVE LOGITS
    ned
    0.09
    auer
    0.08
    note
    0.08
    umed
    0.08
    “
    0.08
    esser
    0.08
    åħ»
    0.08
    nett
    0.08
    jay
    0.08
    nat
    0.08
    Activations Density 0.025%

    No Known Activations