© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    ä¸ĵä¸ļæĬĢæľ¯
    -0.11
    å³Ĵ
    -0.10
    ENO
    -0.10
    åı£æ°´
    -0.09
    ltk
    -0.09
    ä¸Ģç¯ĩæĸĩç«ł
    -0.09
    çĭĦ
    -0.08
    ä¸Ģ项
    -0.08
    åĩºéģĵ
    -0.08
    éĴ®
    -0.08
    POSITIVE LOGITS
    大æ¦Ĥ
    0.09
    èĥ½å¾ĹåĪ°
    0.09
    fon
    0.09
    ä¸Ĭåİ»
    0.09
    å°½
    0.09
    åıĭ好
    0.09
     bri
    0.09
    éĿĴæĺ¥
    0.09
    brane
    0.09
     táºŃn
    0.09
    Activations Density 0.002%

    No Known Activations