© 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. 53426
    Prev
    Next
    INDEX
    Explanations

    by-election, bylaw, Byzantine, bystander

    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
    ~~
    -0.10
    ç¼ĵ
    -0.10
    éĩįå¿ĥ
    -0.09
    åŁºéĩijä¼ļ
    -0.09
    çļĦ女åŃ©
    -0.09
    низ
    -0.09
    iless
    -0.08
     ÑģоÑĨиалÑĮно
    -0.08
    اغ
    -0.08
    mpi
    -0.08
    POSITIVE LOGITS
    entifier
    0.09
    èĩ¾
    0.09
    èĭĹ
    0.08
    èµ·
    0.08
    à¸ĺรรม
    0.08
    ä»ĺåĩº
    0.08
    ymm
    0.08
    Ñģкое
    0.08
     Cobb
    0.08
    rees
    0.08
    Activations Density 0.005%

    No Known Activations