© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36546
    Prev
    Next
    INDEX
    Explanations

    Jamestown or Johnstown

    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
    迹
    -0.09
    cour
    -0.08
    æĵį
    -0.08
    æŃ£æĸĩ
    -0.08
     Agency
    -0.08
    åIJĪæł¼
    -0.08
    æľĢå¿«
    -0.08
    .undo
    -0.08
    è·¡
    -0.08
    è´§
    -0.08
    POSITIVE LOGITS
    éű
    0.10
    è¿ĽäºĨ
    0.10
    åĹĶ
    0.10
    æĹ©æĻļ
    0.09
    ROP
    0.09
    лÑıÑĢ
    0.08
    对她
    0.08
     Reese
    0.08
     suff
    0.08
    asha
    0.08
    Activations Density 0.002%

    No Known Activations