© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51265
    Prev
    Next
    INDEX
    Explanations

    spoken words and sign language

    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
    /doc
    -0.10
    ç»®
    -0.10
    è±¹
    -0.09
    æ·Ħ
    -0.09
    iglia
    -0.09
    asting
    -0.09
    浪
    -0.09
    æįĨ
    -0.09
    éľĦ
    -0.09
    eya
    -0.09
    POSITIVE LOGITS
    çľĭä¸įè§ģ
    0.09
    溯æºIJ
    0.08
    igan
    0.08
    whatever
    0.08
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
    æľīæĦıä¹ī
    0.08
     Sue
    0.08
    å®ŀçī©
    0.08
    -License
    0.08
     Horton
    0.08
    Activations Density 0.074%

    No Known Activations