© 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. 55932
    Prev
    Next
    INDEX
    Explanations

    ell-

    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
    å¾ħ
    -0.09
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    å¼ķ
    -0.08
    eki
    -0.08
    urdy
    -0.08
    çļĩåĨł
    -0.08
    ä»ĺ款
    -0.08
    atori
    -0.08
    tube
    -0.08
    atically
    -0.07
    POSITIVE LOGITS
    æĮĤçĿĢ
    0.09
    åº
    0.09
    è¾ĥéĩı
    0.09
    ernet
    0.08
    æį
    0.08
    缸符
    0.08
    æĿ¥ä¸įåıĬ
    0.08
    ilitation
    0.08
    çĵ¿
    0.08
     friday
    0.08
    Activations Density 0.401%

    No Known Activations