© 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. 33131
    Prev
    Next
    INDEX
    Explanations

    men and women

    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
    ç³ł
    -0.11
    å¾ĹçĽĬ
    -0.10
    çĵł
    -0.10
    楼
    -0.09
    è¿Ļè¯Ŀ
    -0.09
    ç®Ģ约
    -0.09
    èģĶè°Ĭ
    -0.09
    çĶ·æĢ§
    -0.09
    AUT
    -0.09
    åī¥ç¦»
    -0.09
    POSITIVE LOGITS
    á»Ķ
    0.09
    หลาà¸ģหลาย
    0.09
    éĢĴ
    0.09
    çī¹åĪ«å£°æĺİ
    0.08
    liner
    0.08
    _already
    0.08
     LoggerFactory
    0.08
    åĪĩæį¢
    0.08
    aldo
    0.08
    singleton
    0.08
    Activations Density 0.010%

    No Known Activations