© 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. 63583
    Prev
    Next
    INDEX
    Explanations

    Eldorado, Rail, Contract

    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
     Friendly
    -0.09
    ë£Į
    -0.08
    .gnu
    -0.08
    .ca
    -0.08
    friends
    -0.08
     prox
    -0.08
    ık
    -0.08
    undai
    -0.08
     defer
    -0.08
    ôle
    -0.08
    POSITIVE LOGITS
    æ¿Ģ
    0.11
    ense
    0.10
    æ¹¿åľ°
    0.09
    çIJ
    0.09
    ä¸įæĸŃçļĦ
    0.09
    æ¯Ĵåĵģ
    0.08
    posites
    0.08
    æĿ¯åŃIJ
    0.08
    quan
    0.08
    第åħŃ
    0.08
    Activations Density 0.007%

    No Known Activations