© 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. 27517
    Prev
    Next
    INDEX
    Explanations

    surgical procedures and treatments

    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
    桦
    -0.09
    客æµģ
    -0.09
    èĥ¼
    -0.09
    ä»°
    -0.08
    çĭ©
    -0.08
    åİŁæľ¬
    -0.08
    è°ģèĥ½
    -0.08
    éŀ
    -0.08
    æįħ
    -0.08
    è¡Ģ液循çݯ
    -0.08
    POSITIVE LOGITS
    åºĬä¸Ĭ
    0.09
    Ĥ¬
    0.09
    ä¸Ģ带
    0.09
     Emin
    0.09
    åľ¨åŃ¦æł¡
    0.08
    临
    0.08
    åŁĭ
    0.08
    åĩºå¢ĥ
    0.08
    metis
    0.08
    .executeUpdate
    0.08
    Activations Density 0.146%

    No Known Activations