© 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. 6531
    Prev
    Next
    INDEX
    Explanations

    animal behavior

    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
    ç±³ç²ī
    -0.09
    edy
    -0.09
    å¿įåıĹ
    -0.09
    -paid
    -0.09
    paid
    -0.09
    çł
    -0.09
    ellt
    -0.08
    çļĦæīĭ
    -0.08
    æݧåĪ¶ç³»ç»Ł
    -0.08
    è¿Ļ个æĹ¶ä»£
    -0.08
    POSITIVE LOGITS
    istic
    0.13
     animals
    0.09
     animal
    0.09
    ApiClient
    0.09
    åĬ¨çī©
    0.09
    ãĤĤãģ®ãģ®
    0.09
     kingdom
    0.09
    é©®
    0.09
    olk
    0.09
    ATTER
    0.09
    Activations Density 0.077%

    No Known Activations