© 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. 10025
    Prev
    Next
    INDEX
    Explanations

    actions or processes

    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
    SN
    -0.09
    èĤ¤
    -0.09
    åħ¶æīĢ
    -0.09
    åĨĻä¸ĭ
    -0.09
    æĥ³äºĨæĥ³
    -0.08
    WN
    -0.08
    æİīäºĨ
    -0.08
    ÑĥÑĤÑĮ
    -0.08
     Äijáo
    -0.08
    åĶ®
    -0.08
    POSITIVE LOGITS
    第ä¸Ģ次
    0.11
    管çIJĨä¸Ńå¿ĥ
    0.10
    æŁIJç§į
    0.09
    åĪĿ次
    0.09
    åıªæĺ¯
    0.09
    ãģĵãĤĮãģĭãĤī
    0.08
    é¦ĸ次
    0.08
    çļĦ人æĿ¥è¯´
    0.08
    enger
    0.08
    åĪĿãĤģãģ¦
    0.08
    Activations Density 0.189%

    No Known Activations