© 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. 33732
    Prev
    Next
    INDEX
    Explanations

    Proof coin

    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
    unky
    -0.10
    æµģ泪
    -0.10
     Watson
    -0.10
    smarty
    -0.09
    稻
    -0.09
    æĪ¿ä¸ľ
    -0.09
    çļĦ缮åħī
    -0.09
    å¥ł
    -0.08
    éĺ¶
    -0.08
    è¿Ŀ约
    -0.08
    POSITIVE LOGITS
    éĵ¸éĢł
    0.11
    mint
    0.11
     mint
    0.10
    éĶ»éĢł
    0.10
     Mint
    0.09
    inas
    0.09
    èĸ®
    0.09
    apiro
    0.09
    éĵľ
    0.09
    ãģĹãģŁãĤĤãģ®
    0.08
    Activations Density 0.057%

    No Known Activations