© 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. 33564
    Prev
    Next
    INDEX
    Explanations

    occupational roles and professions

    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
    示èĮĥ
    -0.09
    eyer
    -0.08
    REC
    -0.08
    é¾ĻéŨ
    -0.07
    æĹ¶ä»£
    -0.07
    æ¯įæł¡
    -0.07
    ãģĦãģıãĤī
    -0.07
    apiro
    -0.07
     Founder
    -0.07
    æľ½
    -0.07
    POSITIVE LOGITS
    çļĭ
    0.10
    æĸ°çĶŁ
    0.10
    ä»İäºĭ
    0.10
     обÑģлÑĥжива
    0.09
    è¦ģç´§
    0.09
    .faces
    0.09
    inton
    0.09
    覺
    0.09
    ä¸Ģçľĭ
    0.09
    ä¸įä¹ħ
    0.09
    Activations Density 0.107%

    No Known Activations