© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    each of these

    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
    éĽĢ
    -0.09
    å¦Ĥæŀľè¯´
    -0.09
     Essence
    -0.09
    ãĥĥãĤ¯ãĤ¹
    -0.09
    侯
    -0.08
    çĽĬ
    -0.08
    æĻ°
    -0.08
    åķ¦
    -0.08
     dub
    -0.08
     overall
    -0.08
    POSITIVE LOGITS
    åĽĽä¸ª
    0.11
    åī©ä¸ĭ
    0.11
    åĽĽç§į
    0.10
    é³ŀ
    0.09
    åħŃ个
    0.09
    è¿Ļä¸ī个
    0.09
    ä¸ī项
    0.09
    ä¸ĭä¸Ģ
    0.09
    afil
    0.09
    eso
    0.09
    Activations Density 0.019%

    No Known Activations