© 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. 61853
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    inem
    -0.09
    коÑģ
    -0.09
    unate
    -0.08
    å®ŀè·µä¸Ń
    -0.08
    Hugh
    -0.08
    ä¹³
    -0.08
    VIN
    -0.08
     Eh
    -0.08
    VO
    -0.08
    Spo
    -0.08
    POSITIVE LOGITS
    æĪijåĸľæ¬¢
    0.10
    åIJĦ个
    0.10
    _fixture
    0.10
    æıĦ
    0.10
     fronts
    0.09
    åIJĦ个çݯèĬĤ
    0.09
    羡
    0.09
     Ø£ÙĨØŃاء
    0.08
    å¹²éĥ¨
    0.08
    åIJĦ个æĸ¹éĿ¢
    0.08
    Activations Density 0.127%

    No Known Activations