© 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. 50977
    Prev
    Next
    INDEX
    Explanations

    bowel functions and conditions

    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
    æľīè¿ĩ
    -0.10
    æĶ¾è¿ĩ
    -0.09
    ç³ł
    -0.09
    è¡ĮåĪĹ
    -0.09
    Ky
    -0.09
    çIJĨåıij
    -0.08
    ner
    -0.08
     Ky
    -0.08
    æ¶Īè´¹åįĩ级
    -0.08
    PG
    -0.08
    POSITIVE LOGITS
    izza
    0.10
    çĽijå¯Ł
    0.09
    aina
    0.09
    ä¸Ģç¬Ķ
    0.09
    翼
    0.09
    æ¯ĶæĪij
    0.09
    å¤§åľ°
    0.08
    íĺģ
    0.08
    è¡·
    0.08
     fav
    0.08
    Activations Density 0.035%

    No Known Activations