© 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. 6428
    Prev
    Next
    INDEX
    Explanations

    Poplar Street

    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
     Alo
    -0.09
    orno
    -0.09
    igu
    -0.09
    èij¡
    -0.09
    elda
    -0.09
    ping
    -0.09
    æĤĮ
    -0.09
    èĸ·
    -0.09
    rug
    -0.09
    arella
    -0.08
    POSITIVE LOGITS
    æĢ»èµĦ产
    0.09
    èĪį
    0.08
    åĩĮæĻ¨
    0.08
    棺
    0.08
     Lawson
    0.08
    澤
    0.08
    宽æķŀ
    0.08
    åĮł
    0.08
    illegal
    0.08
    lash
    0.08
    Activations Density 0.003%

    No Known Activations