© 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. 62525
    Prev
    Next
    INDEX
    Explanations

    vitamin B compounds

    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
    ëĿ¼ëıĦ
    -0.09
    ãĤ½ãĥ³
    -0.09
    课å¤ĸ
    -0.08
    aint
    -0.08
    绳
    -0.08
    æ·Ļ
    -0.08
    è¿Ļæł·çļĦè¯Ŀ
    -0.08
    产èĥ½
    -0.08
     hairy
    -0.08
    ä¸ŃéĢĶ
    -0.08
    POSITIVE LOGITS
    群
    0.10
    ç´łè´¨
    0.10
    resh
    0.09
    çĶŁç´ł
    0.09
    åij²
    0.09
    çŃĭ
    0.09
    èĵĬ
    0.09
    丸
    0.09
    ires
    0.08
    é«ĥ
    0.08
    Activations Density 0.037%

    No Known Activations