© 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. 32507
    Prev
    Next
    INDEX
    Explanations

    gastric and gastrointestinal

    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
    çĥ¬
    -0.09
    éģ¿
    -0.09
    çľ¼åīįçļĦ
    -0.09
    è¹ij
    -0.09
    ipient
    -0.09
    åı²ä¸ĬæľĢ
    -0.09
    NIC
    -0.09
    ivil
    -0.09
    omb
    -0.09
    IOS
    -0.09
    POSITIVE LOGITS
    abilities
    0.10
    عÙĨ
    0.09
    ä¸Ģéĺµ
    0.09
    vik
    0.09
    ä¸ĩåįĥ
    0.09
    æѤæĸĩ
    0.08
    дан
    0.08
    Ùħض
    0.08
     Hawk
    0.08
    æ³ģ
    0.08
    Activations Density 0.050%

    No Known Activations