© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51311
    Prev
    Next
    INDEX
    Explanations

    flow rate

    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
    伸
    -0.09
    åĪ°å¤Ħ
    -0.09
    èĨĪ
    -0.09
     pyl
    -0.09
    åĽĽå¤Ħ
    -0.09
    被è§Ĩ为
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
     penetr
    -0.08
    éĶŃ
    -0.08
    æ½ĩ
    -0.08
    POSITIVE LOGITS
    æµģéĩı
    0.13
     flow
    0.13
    æµģçķħ
    0.12
    à¹Ħหล
    0.12
    flow
    0.11
     rate
    0.11
    æµģåĬ¨
    0.10
    顺çķħ
    0.10
    ä¸ĢèĤ¡
    0.10
    rate
    0.10
    Activations Density 0.209%

    No Known Activations