© 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. 38652
    Prev
    Next
    INDEX
    Explanations

    kids pool

    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
    è¿Ļæł·çļĦè¯Ŀ
    -0.10
    æĪIJåĵģ
    -0.08
    enze
    -0.08
    è´¬
    -0.08
    ç¦Ĭ
    -0.08
    åıįæĢĿ
    -0.08
    ä¸Ģé¡¿
    -0.08
    peak
    -0.08
    è¿Ļä¹Ī说
    -0.08
     Arb
    -0.08
    POSITIVE LOGITS
    æĹłå¿§
    0.10
    çİ©åħ·
    0.10
    çİĭåĽ½
    0.10
    çİ©
    0.10
    æīĵ
    0.10
    ç³ĸæŀľ
    0.09
     Flem
    0.09
    åį¡éĢļ
    0.09
    ouce
    0.09
    icolon
    0.09
    Activations Density 0.058%

    No Known Activations