© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2817
    Prev
    Next
    INDEX
    Explanations

    shooting massacre

    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
    åıĬ缸åħ³
    -0.10
    ä¸Ģé»ŀ
    -0.08
    çĵ¤
    -0.08
    ':''
    -0.08
    çĵľ
    -0.08
    çĶŁäº§çĶŁæ´»
    -0.08
    äºĨå¤ļå°ij
    -0.08
    让å®ĥ
    -0.08
    é¾Ħ
    -0.08
    çĵ¢
    -0.08
    POSITIVE LOGITS
     ebenfalls
    0.11
    åIJĮæł·
    0.10
    åIJĮæł·æĺ¯
    0.10
     ÑĤоже
    0.09
     likewise
    0.08
    åħ¬ç½ijå®īå¤ĩ
    0.08
    æļ¨
    0.08
    ksen
    0.08
    ATIC
    0.08
    ÐķÐĿ
    0.08
    Activations Density 0.423%

    No Known Activations