© 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. 29959
    Prev
    Next
    INDEX
    Explanations

    what was

    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
    izada
    -0.09
    马路
    -0.08
    çļĦåĦ¿åŃIJ
    -0.08
    äºĶä¸Ģ
    -0.08
    horn
    -0.08
     Ñ
    -0.08
    éĤ£ç§į
    -0.08
    ä»Ģ麽
    -0.07
    çĶŁæĢģæĸĩæĺİ
    -0.07
    帮
    -0.07
    POSITIVE LOGITS
    chin
    0.10
    称为
    0.10
    itre
    0.09
    被称为
    0.09
    欢
    0.09
    èħ¹
    0.09
    å·²ç»ıåľ¨
    0.09
    ä¸Ģçľĭ
    0.09
    åı«åģļ
    0.09
    çĻ½è¡£
    0.09
    Activations Density 0.041%

    No Known Activations