© 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. 9867
    Prev
    Next
    INDEX
    Explanations

    all or everything

    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
    ä¸Ģèµ·
    -0.09
    å§Ĭ
    -0.08
    åĪ¶æĪIJ
    -0.08
     unanim
    -0.08
     CONSTANT
    -0.08
    ray
    -0.08
    ä¸Ģè¶Ł
    -0.08
    大æ¦Ĥ
    -0.08
    åĪ¶åĵģ
    -0.08
     somewhere
    -0.08
    POSITIVE LOGITS
    衲
    0.12
    æİĸ
    0.10
    è¿ĩå¾Ģ
    0.10
    æĬĽ
    0.10
    zeÅĽ
    0.10
    äºĭä¸ļ
    0.09
    èĩ³æѤ
    0.09
     Svens
    0.09
    нÑĥÑĤ
    0.09
    éĽªèĬ±
    0.09
    Activations Density 0.028%

    No Known Activations