© 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. 21621
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation followed by starts

    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
    çıł
    -0.08
     Polo
    -0.08
    çĮ
    -0.08
    ä¾®
    -0.08
    oftware
    -0.08
    ä¸įå¾Ĺä¸į
    -0.08
    rew
    -0.08
    ober
    -0.08
    çļĦ人çĶŁ
    -0.08
    çľģæķĻèĤ²
    -0.08
    POSITIVE LOGITS
    æıIJè®®
    0.13
    åij¼åIJģ
    0.13
    åij¼å£°
    0.12
    建议
    0.12
    æĹ©æĹ¥
    0.11
    åIJ¬åIJ¬
    0.11
    æľĢ好æĺ¯
    0.10
    以便
    0.10
    çļĦæĦ¿æľĽ
    0.10
    æľīæĿ¡ä»¶çļĦ
    0.10
    Activations Density 0.119%

    No Known Activations