© 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. 51197
    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
    åķ§
    -0.10
    æľ¬ç½ij
    -0.10
    ewise
    -0.10
    æĬķèŀįèµĦ
    -0.09
    åĤ¾
    -0.09
    antz
    -0.09
    _hint
    -0.09
    gow
    -0.09
    æ¤ħ
    -0.09
    çŃļ
    -0.09
    POSITIVE LOGITS
    åĽłä¸ºæĪij们
    0.10
    æ¯ı次
    0.10
    åĽłä¸º
    0.09
     because
    0.08
    åĽłä¸ºå®ĥ
    0.08
    åĽłä¸ºæĪij
    0.08
     brake
    0.08
    åĽłä¸ºåľ¨
    0.08
    éĻ¤éĿŀ
    0.08
    Because
    0.08
    Activations Density 0.094%

    No Known Activations