© 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. 61407
    Prev
    Next
    INDEX
    Explanations

    comparative statements using than

    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
    OLA
    -0.09
    æĭ³
    -0.09
     صØŃ
    -0.08
    æ·Ģ
    -0.08
    enÃŃ
    -0.08
    lem
    -0.08
    åĪº
    -0.08
    å±ķ示äºĨ
    -0.08
    pla
    -0.08
    溲
    -0.08
    POSITIVE LOGITS
    å®ģåİ¿
    0.10
    å¾½
    0.10
    å¦Ĥæľīä¾µæĿĥ
    0.10
    让æĤ¨
    0.09
    ä¹Łä¸įæķ¢
    0.09
    让çĶ¨æĪ·
    0.09
    çļĦ姿æĢģ
    0.09
    éĹ¯
    0.09
    ç¥ŀéĢļ
    0.09
    ä¹ĭ举
    0.09
    Activations Density 0.025%

    No Known Activations