© 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. 2341
    Prev
    Next
    INDEX
    Explanations

    punctuation or connecting words followed by words

    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
    éĻĮ
    -0.09
    梦è§ģ
    -0.09
     ÑģÑĤÑĢаÑħ
    -0.08
    æĦıå¢ĥ
    -0.08
     Howe
    -0.08
    æļĹæļĹ
    -0.08
    lopedia
    -0.08
    .fi
    -0.08
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    çģ°èī²
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.12
    ä¸Ģæł·
    0.11
    ä¸Ģæł·çļĦ
    0.10
    èĪ¬
    0.10
    æºIJæºIJä¸įæĸŃ
    0.09
    æł·çļĦ
    0.09
    ä¸įçŁ¥
    0.09
    ä¸Ģ樣
    0.09
    è¯¥é¡¹çĽ®
    0.09
    æī¾åĩĨ
    0.08
    Activations Density 0.051%

    No Known Activations