© 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. 8983
    Prev
    Next
    INDEX
    Explanations

    political platform

    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
    çĽħ
    -0.10
    æī®
    -0.09
    ë£Į
    -0.09
    ellery
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    åīįéĢĶ
    -0.08
    FromArray
    -0.08
    åºķèķ´
    -0.08
    aspers
    -0.08
    imens
    -0.08
    POSITIVE LOGITS
    atic
    0.10
    arity
    0.10
    arser
    0.10
    å³Ļ
    0.10
    ä¸įä¸ĭ
    0.10
    ter
    0.09
    é²Ĥ
    0.09
    ATIC
    0.09
    odore
    0.09
    è¿Ħ
    0.09
    Activations Density 0.025%

    No Known Activations