© 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. 18218
    Prev
    Next
    INDEX
    Explanations

    drugs and chemicals

    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
    被åĬ¨
    -0.10
    éļĹ
    -0.09
    llib
    -0.09
    å¯Ĵ
    -0.09
    æİĪ
    -0.09
    .bundle
    -0.09
    è¡¥åĬ©
    -0.09
    AÃĩÃĥO
    -0.08
    åĺī
    -0.08
    åı°
    -0.08
    POSITIVE LOGITS
    åı¯èĥ½å¯¼èĩ´
    0.11
    åį±éĻ©
    0.11
     rapid
    0.10
    æŀģæĺĵ
    0.09
    æŀģé«ĺ
    0.09
     rapidly
    0.09
    è´¸
    0.09
    å¾Īåı¯èĥ½
    0.09
    è¡Ĺ头
    0.09
    è¿Ŀ
    0.09
    Activations Density 0.078%

    No Known Activations