© 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. 8709
    Prev
    Next
    INDEX
    Explanations

    domestic animals and cultivation

    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
    éģ®
    -0.09
    ç¤ģ
    -0.09
     Jonas
    -0.08
     parity
    -0.08
    IOR
    -0.08
    hti
    -0.08
    è·ĭ
    -0.08
    æĹ¥å¤ľ
    -0.08
    åŁ·
    -0.08
     shaded
    -0.08
    POSITIVE LOGITS
    驯
    0.11
    èµ·æĿ¥
    0.10
     domestic
    0.10
    饲åħ»
    0.09
    åħ¼èģĮ
    0.09
    åı¯æݧ
    0.09
     domest
    0.09
    åĸĤ
    0.09
    èĦĨ
    0.09
     пиÑĤ
    0.09
    Activations Density 0.135%

    No Known Activations