© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9555
    Prev
    Next
    INDEX
    Explanations

    title: followed by descriptive text

    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
    åĿ³
    -0.08
    ä¸įåı¯
    -0.08
    ŀæĢ§
    -0.08
    æݨèįIJéĺħ读
    -0.08
    å²Ī
    -0.07
    å·§åħĭ
    -0.07
    ä½į
    -0.07
    çĤ½
    -0.07
    å·
    -0.07
     Battles
    -0.07
    POSITIVE LOGITS
    客æĪ·æľįåĬ¡
    0.09
    欢è¿İæĤ¨
    0.09
    èIJ¥
    0.09
    çĶŁæĢģä¿ĿæĬ¤
    0.08
    åľ°éģĵ
    0.08
    åĹŁ
    0.08
    GINE
    0.08
    creen
    0.08
    CAF
    0.08
    被æįķ
    0.08
    Activations Density 1.004%

    No Known Activations