© 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. 30344
    Prev
    Next
    INDEX
    Explanations

    nominations, nominated, suggestions

    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
    çĹĽ
    -0.09
    èIJ½æĪ·
    -0.09
    çŃ¾è®¢
    -0.09
     mãi
    -0.08
    lite
    -0.08
    åĨł
    -0.08
    çŃ¾åŃĹ
    -0.08
    æľŁå¾ħ
    -0.08
    贯彻
    -0.08
    inke
    -0.08
    POSITIVE LOGITS
    æıIJåIJį
    0.14
    åĢĻéĢī
    0.12
    è¯ĦéĢī
    0.11
     nominations
    0.11
    äºĭ迹
    0.11
    åĢĻéĢī人
    0.10
    æ¡Ģ
    0.10
     nominated
    0.10
    身边çļĦ
    0.10
    符åIJĪæĿ¡ä»¶
    0.10
    Activations Density 0.024%

    No Known Activations