© 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. 2223
    Prev
    Next
    INDEX
    Explanations

    questions about how or why

    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
    agle
    -0.08
    pers
    -0.08
    ä½ıå®ħ
    -0.08
     (?)
    -0.08
     ?????
    -0.08
     TECH
    -0.08
    าà¸ĩ
    -0.08
    ãģķãģĪ
    -0.08
     Pand
    -0.08
     dy
    -0.07
    POSITIVE LOGITS
    åģļåĪ°
    0.11
    è¿ĻæŶåĢĻ
    0.10
    æŃ£å½ĵ
    0.10
    è¿ĻæŶ
    0.10
    åĿļå®ļä¸į移
    0.09
    æĸ¹åľĨ
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    é£ŀæī¬
    0.09
     Liberation
    0.09
    è¿Ļ个æŶåĢĻ
    0.09
    Activations Density 0.307%

    No Known Activations