© 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. 30295
    Prev
    Next
    INDEX
    Explanations

    writing down the rules

    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
     пÑĢеж
    -0.09
     Mansion
    -0.09
    aÄĩ
    -0.09
    akah
    -0.08
    åķĨæĬ¥
    -0.08
     Sab
    -0.08
    ycz
    -0.08
    aju
    -0.08
    rent
    -0.08
    Sab
    -0.08
    POSITIVE LOGITS
    ä¸ĭæĿ¥çļĦ
    0.11
    GRES
    0.10
    ä¸ĭæĿ¥
    0.10
    ä»Ģä¹Īæĺ¯
    0.09
    -pad
    0.09
    æĹĮ
    0.09
    .INSTANCE
    0.09
    ÑĤÑĥÑĢ
    0.09
    ALLE
    0.09
    çªľ
    0.09
    Activations Density 0.029%

    No Known Activations