© 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. 31358
    Prev
    Next
    INDEX
    Explanations

    Wait, seen, listen, imagine, try

    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
    æ£ķ
    -0.09
    ä½į
    -0.09
    带走
    -0.09
    ä¸ĢåĪĩ
    -0.08
    æľīéĴĪ对æĢ§
    -0.08
    æĪĸå¤ļæĪĸå°ij
    -0.08
    RICS
    -0.08
    éĻIJ
    -0.08
    ACY
    -0.08
    ldr
    -0.08
    POSITIVE LOGITS
    çľĭçľĭ
    0.14
    æĿ¥çľĭçľĭ
    0.11
    åİ»çľĭçľĭ
    0.10
    çľĭä¸Ģçľĭ
    0.10
    åıªè§ģ
    0.10
    åIJ¬åIJ¬
    0.10
    éĹ®éĹ®
    0.10
    æĦıè§ģåıįé¦Ī
    0.09
    çľĭä¸Ģä¸ĭ
    0.09
    ä¸ĭ游
    0.09
    Activations Density 0.041%

    No Known Activations