© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19444
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    ç±³åħ°
    -0.09
    ä¸Ŀ毫ä¸į
    -0.09
     Examiner
    -0.09
    çŃīçŃī
    -0.08
    ä¸ĬçĻ¾
    -0.08
    ç²¼
    -0.08
    æĥķ
    -0.08
    å¦ĤåIJĮ
    -0.08
    itta
    -0.08
    çļĦ人çī©
    -0.08
    POSITIVE LOGITS
    è¿Ļ件äºĭ
    0.10
    è
    0.09
    .tk
    0.09
     поÑĤомÑĥ
    0.09
    èĢĮå·²
    0.09
     TK
    0.09
    å®ŀå®ŀåľ¨åľ¨
    0.09
    ä¸į太好
    0.08
    æŀģåħ¶
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
    Activations Density 0.260%

    No Known Activations