© 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. 27754
    Prev
    Next
    INDEX
    Explanations

    latest updates and trends

    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
    ä¸įåĪĨ
    -0.09
    家åĽŃ
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    izen
    -0.09
    èĢģèĻİ
    -0.08
    觥
    -0.08
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.07
     Kam
    -0.07
    å¼ĢåIJ¯äºĨ
    -0.07
    çĴŀ
    -0.07
    POSITIVE LOGITS
    æľĢæĸ°çļĦ
    0.24
    åīį沿
    0.24
    æľĢæĸ°
    0.22
     latest
    0.18
    ä¸İæĹ¶ä¿±è¿Ľ
    0.18
    latest
    0.17
    /latest
    0.15
    ç´§è·Ł
    0.15
    æĸ°æĬĢæľ¯
    0.15
     newest
    0.15
    Activations Density 0.104%

    No Known Activations