© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49307
    Prev
    Next
    INDEX
    Explanations

    Locke, Brooker, Bullock

    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
    pered
    -0.09
     inherited
    -0.08
    ernet
    -0.08
    èĨĢ
    -0.08
    å·´é»İ
    -0.08
    actic
    -0.08
    enge
    -0.08
    igne
    -0.08
    rot
    -0.08
    ợi
    -0.08
    POSITIVE LOGITS
    çĪ·
    0.12
    å½ĺ
    0.11
    æ»ĭåij³
    0.10
    èģ¿
    0.10
    EXT
    0.09
    åĵĦ
    0.09
    éĶ®çĽĺ
    0.09
    èıĸ
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    รา
    0.09
    Activations Density 0.001%

    No Known Activations