© 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. 27339
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
    ials
    -0.12
    çİ¢
    -0.10
    çºłæŃ£
    -0.09
    çļ¿
    -0.09
    istic
    -0.09
    éĽĦåİļ
    -0.08
    è¯Ī
    -0.08
    hta
    -0.08
    天ä¸ĭ
    -0.08
    æµ·å¤ĸå¸Ĥåľº
    -0.08
    POSITIVE LOGITS
    åį«è§Ĩ
    0.13
    çŃ
    0.10
    çĴĢ
    0.10
     обеÑģп
    0.09
    佬
    0.09
    ucker
    0.09
    çĿĩ
    0.09
    -based
    0.09
    abay
    0.09
    duino
    0.08
    Activations Density 0.014%

    No Known Activations