© 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. 11105
    Prev
    Next
    INDEX
    Explanations

    costs, fees, and expenses

    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
    åĩłçĤ¹
    -0.09
    åĪĥ
    -0.09
    éĩįè§Ĩ
    -0.09
    ä¸īçĤ¹
    -0.08
     ÑĦин
    -0.08
    .require
    -0.08
    éĢłçº¸
    -0.08
    究竣
    -0.08
     Alvarez
    -0.08
    fic
    -0.08
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.09
    emaker
    0.08
    å¼Ĥåľ°
    0.08
    è¿Ļä¸Ģ次
    0.08
    è¿Ļä¸Ģå¹´
    0.08
    è¿Ļ次
    0.08
    æĪijå½ĵæŶ
    0.08
    å¿ħè¦ģçļĦ
    0.08
    ieder
    0.08
    çħ
    0.08
    Activations Density 0.041%

    No Known Activations