© 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. 9799
    Prev
    Next
    INDEX
    Explanations

    online resources and websites

    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
    çıī
    -0.09
    imeo
    -0.09
    æĻ®éĢļ人
    -0.09
    å°Ĩ士
    -0.09
    èģĮä¸ļæĬĢèĥ½
    -0.08
    åıijå±ķ缮æłĩ
    -0.08
    åĩºåİĤ
    -0.08
    è¿©
    -0.08
    èµ°è·¯
    -0.08
    åįĹè·¯
    -0.08
    POSITIVE LOGITS
    èµĦæºIJ
    0.15
    à¹ģหล
    0.14
     resources
    0.14
     websites
    0.13
    resources
    0.12
    ç½ijç«Ļ
    0.12
     sources
    0.12
    sources
    0.11
    è³ĩæºIJ
    0.11
     useful
    0.11
    Activations Density 0.114%

    No Known Activations