© 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. 4601
    Prev
    Next
    INDEX
    Explanations

    he/she verbs

    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
    æĥ¯ä¾ĭ
    -0.10
    ä¼łè¯´
    -0.09
    æĪĺçģ«
    -0.09
    hart
    -0.08
    èĮ«çĦ¶
    -0.08
    åĨľä½ľçī©
    -0.08
    åģĩæľŁ
    -0.08
     unfamiliar
    -0.08
    atham
    -0.08
    å°ļ书
    -0.08
    POSITIVE LOGITS
    æĽ¾åľ¨
    0.12
    æĺ¯åĽ½åĨħ
    0.10
    æŃ¤é¡¹
    0.10
    æĽ¾
    0.10
    åľ¨åĽ½åĨħ
    0.09
    ÑģÑĤи
    0.09
    AMA
    0.09
    åīįä¸ĸ
    0.09
    æĽ¾ä»»
    0.09
    ä¸ĢéĿ¢
    0.09
    Activations Density 0.187%

    No Known Activations