© 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. 53006
    Prev
    Next
    INDEX
    Explanations

    take place

    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
    аÑĢаÑĤ
    -0.11
    åħĭåĪ¶
    -0.09
    ä¹ĭéģĵ
    -0.09
    åĨĴåĩº
    -0.09
    edReader
    -0.09
    æĭ¯
    -0.09
    oles
    -0.09
    indh
    -0.09
     Decoration
    -0.09
    èĭ´
    -0.09
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.25
    åıijçĶŁ
    0.25
     happening
    0.22
    çĻ¼çĶŁ
    0.21
     happened
    0.21
    åıijçĶŁçļĦ
    0.21
     occur
    0.21
     happens
    0.20
     occurred
    0.20
    çļĦåıijçĶŁ
    0.20
    Activations Density 0.148%

    No Known Activations