© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    starch and enzyme analysis

    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
    ä¸Ń举
    -0.10
    çīĮ
    -0.08
     ding
    -0.08
    åįľ
    -0.08
    çļĭ
    -0.08
    çıŃ
    -0.08
    èįīåľ°
    -0.08
    æĶ¶
    -0.08
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    -0.08
    å¯Ĵ
    -0.08
    POSITIVE LOGITS
     starch
    0.11
    åĶ¾
    0.11
    æ·Ģç²ī
    0.10
    è¡Ģç³ĸ
    0.10
    æ¿ł
    0.09
    ivel
    0.09
    éĢ¢
    0.09
    空çĻ½
    0.09
    åħ¬çĦ¶
    0.09
    converted
    0.09
    Activations Density 0.107%

    No Known Activations