© 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. 31730
    Prev
    Next
    INDEX
    Explanations

    office or day

    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
    失
    -0.09
    çīµ
    -0.09
    ausible
    -0.09
    åĬłå¿«åıijå±ķ
    -0.09
    æ²IJæµ´
    -0.09
    å°ijå¹´
    -0.08
     Duo
    -0.08
    æİ°
    -0.08
    assage
    -0.08
    å¿Ļ
    -0.08
    POSITIVE LOGITS
    å¤įå·¥
    0.11
     sóc
    0.09
    ÑĢаÐ
    0.09
    Gay
    0.09
    ç¡®
    0.09
    åĬŀåħ¬
    0.09
    ç¹³
    0.09
    ÑĤÑĢа
    0.09
    第ä¸Ģ天
    0.09
    USTER
    0.09
    Activations Density 0.068%

    No Known Activations