© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    common / rare frequency

    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
    çļĦä¸ĢäºĽ
    -0.09
    åĽłåľ°
    -0.09
    IODevice
    -0.08
    RON
    -0.08
    é»ijçĻ½
    -0.08
    çł
    -0.08
    æľĢ大éĻIJ度
    -0.08
    ä¸įå¿į
    -0.08
    æĬĹéľĩ
    -0.08
    æĭħè´Ł
    -0.08
    POSITIVE LOGITS
    常è§ģ
    0.21
    å°ijè§ģ
    0.16
     rare
    0.15
     occurrence
    0.15
    常è§ģçļĦ
    0.15
     common
    0.14
     rarity
    0.14
    æĻ®éģįåŃĺåľ¨
    0.14
    ç½ķè§ģ
    0.14
    æ¯Ķè¾ĥå¤ļ
    0.14
    Activations Density 0.300%

    No Known Activations