© 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. 17205
    Prev
    Next
    INDEX
    Explanations

    erectile dysfunction

    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
    .vaadin
    -0.10
    ulin
    -0.09
    çĶ·å¥³
    -0.09
    æµ´
    -0.09
    asn
    -0.08
    æ´Ľéĺ³
    -0.08
     Mae
    -0.08
    仿
    -0.08
     sticky
    -0.08
     Bra
    -0.08
    POSITIVE LOGITS
    å§ĭ建
    0.09
     пÑĢоÑģ
    0.08
    åħ¨éķĩ
    0.08
    ãĤ¥
    0.08
    æĸĩä¸Ń
    0.08
    ä¼Ĺ人
    0.08
     Archae
    0.08
    byn
    0.08
    é¹³
    0.08
     Pew
    0.08
    Activations Density 0.043%

    No Known Activations