© 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. 8494
    Prev
    Next
    INDEX
    Explanations

    analytical writing and research

    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
    åĢ¾
    -0.10
    计ç®ĹåĻ¨
    -0.10
    溺
    -0.09
    çŁ¥
    -0.09
    music
    -0.09
    éªijè¡Į
    -0.09
    俾
    -0.09
    æįº
    -0.09
    åij½ä¸Ń
    -0.09
    .sep
    -0.09
    POSITIVE LOGITS
    ç»ĵ论
    0.09
    è¯ĬæĸŃ
    0.09
    è¯łéĩĬ
    0.09
    西è£ħ
    0.08
    åħ¬è¯ī
    0.08
    idget
    0.08
    èµıæŀIJ
    0.08
     conclusions
    0.08
    æłĢ
    0.08
     conclusion
    0.08
    Activations Density 0.046%

    No Known Activations