© 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. 5141
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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
    åľ¨æĦı
    -0.10
    åIJĮæĹ¶ä¹Ł
    -0.09
    åIJĮæŶè¿ĺ
    -0.09
    åħ¶å®ĥ
    -0.09
    izedName
    -0.09
    转载请
    -0.09
    æľĢéĩįè¦ģ
    -0.09
    éļĶå£ģ
    -0.08
    åŃĹæł·
    -0.08
    ULER
    -0.08
    POSITIVE LOGITS
    å¤ļå°ij
    0.09
    èĭ¥å¹²
    0.09
    èĬ
    0.08
    ä¸įä½İäºİ
    0.08
    好åĥıæĺ¯
    0.08
    èĢģåħµ
    0.08
    å²Į
    0.08
    æľīéĻIJ
    0.07
    _ue
    0.07
    å¨ģæħij
    0.07
    Activations Density 0.159%

    No Known Activations