© 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. 50178
    Prev
    Next
    INDEX
    Explanations

    computational chemistry and chemical informatics

    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
    æĬ¬
    -0.09
    æģ¯
    -0.08
    ä¸įä¸Ĭ
    -0.08
     Magnet
    -0.08
     Bernardino
    -0.08
    太éĺ³
    -0.08
    æ£ĺ
    -0.08
    ä¸Ģçīĩ
    -0.07
     individuals
    -0.07
    åħ¨åľº
    -0.07
    POSITIVE LOGITS
    åĮĸåѦ
    0.14
    åĮĸåѦåĵģ
    0.14
    åĮĸå·¥
    0.14
    Chem
    0.12
     Chemistry
    0.12
     chemical
    0.11
     Chem
    0.11
     sto
    0.10
     chemistry
    0.10
    èį¯åĵģ
    0.10
    Activations Density 0.595%

    No Known Activations