© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7562
    Prev
    Next
    INDEX
    Explanations

    the + noun

    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
    缸åħ³
    -0.12
    èı©æıIJ
    -0.10
    身影
    -0.10
    äººåľ¨
    -0.08
    人åĬĽ
    -0.08
    缸åħ³äººåijĺ
    -0.08
    æ°ı
    -0.08
    çĶ·äºº
    -0.08
    lew
    -0.08
    æīĭèīº
    -0.08
    POSITIVE LOGITS
     ilk
    0.11
     sorts
    0.10
    ç½ij绾èIJ¥éĶĢ
    0.10
    thalm
    0.09
    æ´¥
    0.09
    éģĦ
    0.09
    course
    0.09
     course
    0.08
    å¤Ħåľ¨
    0.08
    ç©¿ä¸Ĭ
    0.08
    Activations Density 0.150%

    No Known Activations