© 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. 31742
    Prev
    Next
    INDEX
    Explanations

    lengthy container covers hours

    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
    çĵł
    -0.09
    éĤĢ
    -0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.09
    adi
    -0.09
    æĸ°çļĦä¸Ģå¹´
    -0.09
    éŨæĪ·
    -0.09
    YL
    -0.08
     Directorate
    -0.08
    edImage
    -0.08
    éĥ½åĸľæ¬¢
    -0.08
    POSITIVE LOGITS
    æķ´æķ´
    0.14
    åİļåİļçļĦ
    0.13
    满满
    0.13
    ä¸Ģ大åłĨ
    0.11
    åİļåİļ
    0.11
    足足
    0.10
    éķ¿éķ¿çļĦ
    0.10
    æijŀ
    0.10
    éķ¿è¾¾
    0.10
    åıįå¤į
    0.10
    Activations Density 0.100%

    No Known Activations