© 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. 16737
    Prev
    Next
    INDEX
    Explanations

    on the other hand

    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
    mates
    -0.11
    æĸ¹åľĨ
    -0.10
    级以ä¸Ĭ
    -0.10
    istic
    -0.09
    åijµæĬ¤
    -0.09
    ä¸Ģç»Ħ
    -0.09
    俳
    -0.09
    è¿ĽèĢĮ
    -0.09
    ä¸Ģ代
    -0.09
     notamment
    -0.09
    POSITIVE LOGITS
    erman
    0.10
    -sex
    0.10
    atab
    0.09
    çĨŁæĤī
    0.09
    ermen
    0.09
    ÑĢеÑģÑĤ
    0.09
    หมà¸Ķ
    0.08
    elt
    0.08
    iable
    0.08
    æľī个
    0.08
    Activations Density 0.016%

    No Known Activations