© 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. 33142
    Prev
    Next
    INDEX
    Explanations

    X after Y structure

    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
    çIJĨ解åĴĮ
    -0.11
    æģIJæĢķ
    -0.09
    åıĤè§Ĥ
    -0.08
     apprec
    -0.08
    sgi
    -0.08
    tin
    -0.08
    æĹłè®ºå¦Ĥä½ķ
    -0.08
    ti
    -0.08
    è°Ĵ
    -0.07
    avel
    -0.07
    POSITIVE LOGITS
    ä¸įè¡Į
    0.10
    UBY
    0.09
    大è¡Ĺ
    0.09
    جاÙħ
    0.09
    ther
    0.09
    gre
    0.09
    ä¸įæĪIJ
    0.08
    (Configuration
    0.08
    har
    0.08
    /all
    0.08
    Activations Density 0.007%

    No Known Activations