© 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. 50090
    Prev
    Next
    INDEX
    Explanations

    pulse pressure

    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
    اء
    -0.11
    rame
    -0.10
    enton
    -0.10
    eme
    -0.09
    çıŃ主任
    -0.09
    olas
    -0.09
    çĸĻ
    -0.09
    ialis
    -0.09
    å§Ķ书记
    -0.09
    erve
    -0.09
    POSITIVE LOGITS
    aneously
    0.10
    оÑĩек
    0.09
    çĦ¶æĺ¯
    0.09
    /if
    0.09
    .defer
    0.08
    ently
    0.08
    .IntPtr
    0.08
    ãĤ·ãĥ³
    0.08
     shred
    0.08
    кÑĢа
    0.08
    Activations Density 0.034%

    No Known Activations