© 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. 19380
    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
     thus
    -0.10
    ầm
    -0.09
     therefore
    -0.09
    oga
    -0.09
     yet
    -0.08
    çĶļèĩ³è¿ĺ
    -0.08
    äºĨå¾Īå¤ļ
    -0.08
    åĺĽ
    -0.08
    thus
    -0.08
    åį´
    -0.08
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģç§į
    0.12
     коÑĤоÑĢаÑı
    0.11
     коÑĤоÑĢÑĭй
    0.11
    éĻ¤æѤ
    0.10
    åľ¨æѤä¹ĭåīį
    0.10
    åIJİèĢħ
    0.10
    ç»
    0.09
    以åħ¶
    0.09
    éĤ£æĺ¯
    0.09
    æŃ¤äºº
    0.09
    Activations Density 0.231%

    No Known Activations