© 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. 48668
    Prev
    Next
    INDEX
    Explanations

    biography subjects

    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
    御
    -0.09
    åħŃå¹´
    -0.09
    averse
    -0.08
    çĽĪ
    -0.08
    æĸ°å¼Ģ
    -0.08
     newly
    -0.08
    以èī²
    -0.08
     embar
    -0.08
    æĸ°æĬĢæľ¯
    -0.08
    eso
    -0.08
    POSITIVE LOGITS
    人çī©
    0.17
    äºĭ迹
    0.16
    è¿Ļ个人
    0.14
    åı±
    0.14
    çļĦ人çī©
    0.14
    ä¼Ł
    0.14
    æŃ¤äºº
    0.14
    éĢĿä¸ĸ
    0.13
    æŃ»åIJİ
    0.13
    åģī
    0.13
    Activations Density 0.326%

    No Known Activations