© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20387
    Prev
    Next
    INDEX
    Explanations

    eclectic mix

    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
    éĽªå±±
    -0.10
    erial
    -0.09
    ymes
    -0.09
    ãĤĩ
    -0.08
     Alps
    -0.08
    ners
    -0.08
    rock
    -0.08
    rid
    -0.07
    argent
    -0.07
    忧èĻij
    -0.07
    POSITIVE LOGITS
    -minded
    0.12
    ness
    0.10
    ussions
    0.10
    å¤ł
    0.10
    满满
    0.10
    å·²ä¹ħ
    0.10
    å¤ļæł·
    0.10
    å·²ä¹ħçļĦ
    0.10
    æĢ§çļĦ
    0.10
    åı¤æĢª
    0.09
    Activations Density 0.001%

    No Known Activations