© 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. 18019
    Prev
    Next
    INDEX
    Explanations

    the more

    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
    ught
    -0.09
    holding
    -0.09
    è°·
    -0.09
     Harbor
    -0.09
    sdale
    -0.08
    yü
    -0.08
    并ä¸įæĺ¯å¾Ī
    -0.08
     Trojan
    -0.08
    ington
    -0.08
    .pg
    -0.08
    POSITIVE LOGITS
    éű
    0.10
    æĸ°çļĦä¸Ģå¹´
    0.09
    对éĿ¢
    0.09
    åºķæ°Ķ
    0.09
    让æ¶Īè´¹èĢħ
    0.09
    çĬ¶åħĥ
    0.09
    ç¿İ
    0.09
    è¿ĪåIJij
    0.09
    راس
    0.09
    è¿Ķ乡
    0.09
    Activations Density 0.016%

    No Known Activations