© 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. 31380
    Prev
    Next
    INDEX
    Explanations

    sentence ending 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
    åıªèĥ½è¯´
    -0.10
    è¿ĺä¸į
    -0.10
    æ¦ľ
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    è¿ĺè¦ģ
    -0.09
    oti
    -0.09
    ieg
    -0.09
    è¿ĺæľī
    -0.08
    å·®çĤ¹
    -0.08
    bat
    -0.08
    POSITIVE LOGITS
    以åħ¶
    0.10
    å®ĥçļĦ
    0.10
    å®ĥ
    0.10
    åħ±æľī
    0.09
    ä»ĸ表示
    0.09
     nó
    0.09
     Nó
    0.08
    æ¦Ĥæĭ¬
    0.08
    æĹ¨åľ¨
    0.08
    mmo
    0.08
    Activations Density 0.427%

    No Known Activations