© 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. 11830
    Prev
    Next
    INDEX
    Explanations

    circus, religion, insurance, card, mafia, adolescence, tantrum

    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
    åIJĮä¼´
    -0.10
    ä¸¤åľ°
    -0.10
    _ASCII
    -0.09
    ech
    -0.09
    侪
    -0.09
    çĻ¾èĬ±
    -0.09
    oston
    -0.09
    æĹĭ
    -0.08
    ç£ĭ
    -0.08
    èİ«åIJįåħ¶å¦Ļ
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.21
    ä¼¼çļĦ
    0.17
    èĪ¬
    0.17
    -like
    0.16
    å¼ıçļĦ
    0.15
    ä¸Ģæł·çļĦ
    0.13
    ä¸Ģæł·
    0.12
    -esque
    0.10
    ä¸Ģ樣
    0.10
    ndl
    0.09
    Activations Density 0.174%

    No Known Activations