© 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. 61488
    Prev
    Next
    INDEX
    Explanations

    ability and needs

    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
    æĽ´æľī
    -0.10
     Vaugh
    -0.09
    åİĨæĿ¥
    -0.08
    å¾Īæľī
    -0.08
    äºĨä¸Ģ个
    -0.08
    確ãģĭãģ«
    -0.08
    ä¼ĺäºİ
    -0.08
    idy
    -0.08
    ãĤĪãĤĬ
    -0.08
    ç»ĵæĿŁäºĨ
    -0.08
    POSITIVE LOGITS
    åıĪèĥ½
    0.16
    æīįè¡Į
    0.15
    åıĪè¦ģ
    0.14
    ä¸įè¦ģ太
    0.14
    è¦ģæľī
    0.13
    å°½åı¯èĥ½
    0.13
    è¿Ļæł·æīįèĥ½
    0.13
    å°½éĩı
    0.13
    æľīä¸Ģå®ļçļĦ
    0.13
    èĥ½åľ¨
    0.13
    Activations Density 0.367%

    No Known Activations