© 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. 9556
    Prev
    Next
    INDEX
    Explanations

    compel suicide

    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
    èĢģèĻİ
    -0.09
    黳
    -0.08
    éĿ¢èī²
    -0.08
     &)
    -0.08
    æ©«
    -0.08
    åĨ²
    -0.08
    Lost
    -0.08
    _utilities
    -0.08
     brisk
    -0.08
    .groups
    -0.08
    POSITIVE LOGITS
    è¡ĢèĦī
    0.09
    å¿ĥæĻº
    0.09
    亢
    0.09
    åĬłä»¥
    0.09
    çļĦç²¾ç¥ŀ
    0.09
    æĬµåĪ¶
    0.08
    å¾ĪæŃ£å¸¸
    0.08
    çļĦ强大
    0.08
    æľīæľŁå¾ĴåĪij
    0.08
     keyed
    0.08
    Activations Density 0.077%

    No Known Activations