© 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. 30869
    Prev
    Next
    INDEX
    Explanations

    Python list manipulation

    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
    orda
    -0.10
    æĪĺçķ¥æĢ§
    -0.09
    殿åłĤ
    -0.09
    çľº
    -0.08
    æĶĴ
    -0.08
     McM
    -0.08
    ãĤ·ãĤ¢
    -0.08
    ä¸Ģæ³¢
    -0.08
    缴è¾ĸå¸Ĥ
    -0.08
    å·®ä¸įå¤ļ
    -0.08
    POSITIVE LOGITS
    RID
    0.09
    æī§æķĻ
    0.09
    èĩªçĦ¶èĢĮ
    0.09
    èŁĴ
    0.08
     blo
    0.08
    ìłľëıĦ
    0.08
    osen
    0.08
    èĤĩäºĭ
    0.08
    æĹłæīĢ
    0.08
    ired
    0.08
    Activations Density 0.074%

    No Known Activations