© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    if condition

    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
    éĢļè¡Į
    -0.09
    æľ¬çĿĢ
    -0.09
    èł²
    -0.09
    寤
    -0.09
     Cory
    -0.09
    辩è¯ģ
    -0.09
    çľ¼çļ®
    -0.08
    æŀģ大çļĦ
    -0.08
    å¹Ħ
    -0.08
    ä¸Ģå®ļèĥ½
    -0.08
    POSITIVE LOGITS
    æľªèĥ½
    0.12
    è¶ħè¿ĩ
    0.12
    ä½łè§īå¾Ĺ
    0.11
    è¶ħéģİ
    0.10
    ä¸įæŃ¢
    0.10
    ä»»ä½ķä¸Ģ个
    0.10
    åıijçİ°
    0.10
    è¶ħåĩº
    0.10
    å®ŀåľ¨
    0.10
    è¶ħè¿ĩäºĨ
    0.09
    Activations Density 0.049%

    No Known Activations