© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21104
    Prev
    Next
    INDEX
    Explanations

    vascularization, necrosis, fibular graft

    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
    æĵį
    -0.11
    weg
    -0.09
    bic
    -0.08
    urette
    -0.08
    ApiClient
    -0.07
    ADE
    -0.07
    éĻ¶
    -0.07
    åĬĿ
    -0.07
    deo
    -0.07
     Dou
    -0.07
    POSITIVE LOGITS
    она
    0.10
    æĿ¥çĶµ
    0.10
    èĹ
    0.10
    ç²¾ç¾İ
    0.10
    磮
    0.10
    æľīæľŁ
    0.10
    ä¸ŃéĢĶ
    0.09
    æĬĬèĩªå·±çļĦ
    0.09
    æĬ½åĩº
    0.09
    æĬ¥å¤į
    0.09
    Activations Density 0.663%

    No Known Activations