© 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. 53687
    Prev
    Next
    INDEX
    Explanations

    open space

    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
    ä¹į
    -0.09
    缺ä¹ı
    -0.08
     impl
    -0.08
    æ´Ĺ礼
    -0.08
    æĥħåķĨ
    -0.08
    TL
    -0.08
    ä¹ı
    -0.08
    ç¼Ł
    -0.08
    å¼ĢéĢļ
    -0.08
    ä¹ĭä¸ĭ
    -0.08
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.14
    åİŁæľī
    0.13
     пÑĢеж
    0.12
    åĪĿè¡·
    0.11
     intact
    0.10
    çķĻåľ¨
    0.09
    继ç»Ń
    0.09
    ãģ¾ãģ¾
    0.09
    ç²¾é«ĵ
    0.09
    .providers
    0.09
    Activations Density 0.063%

    No Known Activations