© 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. 52681
    Prev
    Next
    INDEX
    Explanations

    dangerous animals

    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
    Nice
    -0.09
     ÑĢа
    -0.09
    VEST
    -0.09
    ç»´å°Ķ
    -0.09
    楼
    -0.09
    å¨ĥå¨ĥ
    -0.08
    ucc
    -0.08
     Giz
    -0.08
    çķĻå®Ī
    -0.08
    Vac
    -0.08
    POSITIVE LOGITS
    æŶåĪ»
    0.13
    大åŀĭ
    0.11
    èĻİ
    0.10
    ä»Ģä¹Īäºĭ
    0.10
    æĸij
    0.10
    éĩİçĶŁåĬ¨çī©
    0.10
    å·¨åŀĭ
    0.10
    åĬ¨çī©åĽŃ
    0.10
    åĸ·
    0.10
    ä¸¤å¼ł
    0.10
    Activations Density 0.287%

    No Known Activations