© 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. 57487
    Prev
    Next
    INDEX
    Explanations

    may followed by have or make

    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
    HN
    -0.09
    sg
    -0.09
    iez
    -0.08
    zi
    -0.08
    åı¯æĥľ
    -0.08
    éĩįçİ°
    -0.08
    çļĦè¡£æľį
    -0.08
    ickle
    -0.08
    uchs
    -0.08
    åıĹåĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    .rand
    0.09
    ister
    0.09
    æ³¥åľŁ
    0.09
    ä¸īå¹´
    0.08
    æ¯Ķä¾ĭ
    0.08
    æĬ¥åºŁ
    0.08
     Wr
    0.08
    麦åħĭ
    0.08
    çľĭä¼¼
    0.08
     worse
    0.08
    Activations Density 0.054%

    No Known Activations