© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7198
    Prev
    Next
    INDEX
    Explanations

    hamlet, hamper

    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
    iro
    -0.11
    gli
    -0.09
    eer
    -0.09
    ç«Ļç«ĭ
    -0.09
    éĹ´çļĦ
    -0.09
    iros
    -0.09
    纪
    -0.08
    ims
    -0.08
    æ®·
    -0.08
    tt
    -0.08
    POSITIVE LOGITS
    oot
    0.11
    oon
    0.10
    ham
    0.10
    åįģ足
    0.10
    åħ
    0.10
    åĩ¼
    0.09
    alysis
    0.09
    å²Ķ
    0.09
    æ§Į
    0.08
    å¸ĤæĶ¿
    0.08
    Activations Density 0.007%

    No Known Activations