© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18988
    Prev
    Next
    INDEX
    Explanations

    cosmopolitan or metropolitan

    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
    Country
    -0.08
    潺
    -0.08
    çħ®
    -0.08
     Romance
    -0.08
     rigid
    -0.08
    rup
    -0.08
    æķ´é½IJ
    -0.08
    å®ŀçī©
    -0.08
    æī®æ¼Ķ
    -0.08
     Bull
    -0.08
    POSITIVE LOGITS
    -minded
    0.11
     гаÑĢ
    0.10
    翳
    0.09
    åıĪ好
    0.09
    缨
    0.09
    ardy
    0.09
    æĩĴå¾Ĺ
    0.09
     оÑĦоÑĢмлен
    0.08
    ity
    0.08
    itas
    0.08
    Activations Density 0.006%

    No Known Activations