© 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. 19249
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    olan
    -0.09
    å½ĸ
    -0.09
    åľ¨äº¬
    -0.08
    庾
    -0.08
    çĬģ
    -0.08
    æĺİæĺİ
    -0.08
    å¿ħéľĢ
    -0.08
    éļıå¤Ħ
    -0.08
    å¸¦ä½ł
    -0.08
    ÙĪÙĦد
    -0.08
    POSITIVE LOGITS
    çķĻè¨Ģ
    0.12
    表æĢģ
    0.10
    èµŀåIJĮ
    0.10
    åıijè¨Ģ
    0.10
    åĮ¿åIJį
    0.10
    è´¡çĮ®
    0.09
    åĽŀå¤į
    0.09
    æĤłæĤł
    0.09
    åıįé¦Ī
    0.09
    æ¿ĢåĬ¨
    0.09
    Activations Density 0.012%

    No Known Activations