© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    phrases starting with common verbs or conjunctions

    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
    ãģĵãĤĵ
    -0.09
    OTO
    -0.08
    è¿ĻéĩĮæĺ¯
    -0.08
    çĶļèĩ³è¿ĺ
    -0.08
    Æ°a
    -0.08
     ìĿ´ë¥¼
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    æĶ¿çŃĸæݪæĸ½
    -0.08
    orraine
    -0.08
    åħ¸
    -0.08
    POSITIVE LOGITS
     ve
    0.08
     supervise
    0.08
    è§īå¾Ĺå¾Ī
    0.08
    eyer
    0.08
    æ¯Ĵ
    0.08
     filmm
    0.08
    建çŃijå¸Ī
    0.08
     superv
    0.08
    å·¥ä½ľå®¤
    0.08
     Wien
    0.08
    Activations Density 0.084%

    No Known Activations