© 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. 7508
    Prev
    Next
    INDEX
    Explanations

    cadmium, mercury, toxic metals

    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
    ogue
    -0.10
    scr
    -0.10
    çĽ²
    -0.09
    åķ¬
    -0.09
    èĮ¸
    -0.09
    å®īæİĴ
    -0.09
    æĭį
    -0.09
    å²Ĺ
    -0.09
    大æłij
    -0.09
    åıijçİ°èĩªå·±
    -0.08
    POSITIVE LOGITS
    害
    0.11
    åį±å®³
    0.11
    æľī害
    0.11
    çļĦåį±å®³
    0.10
    第ä¸Ģ
    0.10
    éĩįéĩijå±ŀ
    0.10
     substances
    0.10
    tober
    0.09
    æľīæ¯Ĵ
    0.09
     hại
    0.09
    Activations Density 0.238%

    No Known Activations