© 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. 63669
    Prev
    Next
    INDEX
    Explanations

    pesticides or 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
    èľĤèľľ
    -0.09
    ancia
    -0.09
    æIJŃ
    -0.09
    è´¨éĩıéĹ®é¢ĺ
    -0.09
    ä¹°äºĨ
    -0.09
    èĽĨ
    -0.09
    çĸ½
    -0.09
    æľį
    -0.09
    æIJŀå¾Ĺ
    -0.09
    顺çĿĢ
    -0.09
    POSITIVE LOGITS
     Emanuel
    0.09
    zan
    0.08
    侯
    0.08
     Avery
    0.08
    uet
    0.08
    åIJ«
    0.08
    avar
    0.07
    åħ¨è¿ĩç¨ĭ
    0.07
    ìħĭ
    0.07
    注
    0.07
    Activations Density 0.303%

    No Known Activations