© 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. 4685
    Prev
    Next
    INDEX
    Explanations

    closing entities or events

    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
    é¢ľ
    -0.10
    港åĮº
    -0.09
    第ä¸ĢæĿ¡
    -0.09
     alone
    -0.09
    lit
    -0.08
    uttle
    -0.08
     Trap
    -0.08
     Fatal
    -0.08
    é¼İ
    -0.08
    oline
    -0.08
    POSITIVE LOGITS
     khá»ıi
    0.13
    åĽłä¸ºå®ĥ
    0.11
    çĶ±äºİ
    0.10
    以åħį
    0.10
    以便
    0.10
    ÑĢев
    0.09
    due
    0.09
    ä¸į符åIJĪ
    0.09
     due
    0.09
    because
    0.09
    Activations Density 0.194%

    No Known Activations