© 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. 11129
    Prev
    Next
    INDEX
    Explanations

    state names followed by government or legal terms

    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
    åľ°å¸¦
    -0.10
    éģ¥è¿ľ
    -0.09
    å½ĵåľ°äºº
    -0.08
    .Fields
    -0.08
    ãĤ³ãĥŁãĥ¥ãĥĭ
    -0.08
    æ¸ĹéĢı
    -0.08
     оÑĦоÑĢм
    -0.08
    大çģ«
    -0.08
    带éĺŁ
    -0.08
    apr
    -0.08
    POSITIVE LOGITS
    -wide
    0.11
    èĮĥåĽ´åĨħ
    0.10
    çī¹èī²çļĦ
    0.10
    åIJĦ级
    0.09
    ä¸Ģåħ±
    0.09
    éĿ¢ä¸Ĭ
    0.09
    æĽ´å¥½çļĦ
    0.09
    ä¸Ģ举
    0.09
     Genius
    0.09
    å§Ķç»Ħç»ĩéĥ¨
    0.09
    Activations Density 0.189%

    No Known Activations