© 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. 8082
    Prev
    Next
    INDEX
    Explanations

    career milestones

    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
    æĪIJäºĨ
    -0.09
    rown
    -0.09
     sức
    -0.08
    çŃ
    -0.08
    anc
    -0.08
    å½ĵæŶçļĦ
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    fir
    -0.08
     Markets
    -0.08
     HUGE
    -0.08
    POSITIVE LOGITS
    缮åīį为æŃ¢
    0.10
    å¼Ī
    0.09
    åĹŁ
    0.09
    åı¯åĪĨ为
    0.09
    zia
    0.09
    åĿİåĿ·
    0.09
    篷
    0.09
    æĺŁçº§éħĴåºĹ
    0.09
    еж
    0.09
    åİĨç¨ĭ
    0.09
    Activations Density 0.065%

    No Known Activations