© 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. 33023
    Prev
    Next
    INDEX
    Explanations

    import, collection, data, trade, growth

    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
    åħ¸åŀĭçļĦ
    -0.09
    blr
    -0.09
    è¹ĭ
    -0.09
     пÑĢедÑĥÑģ
    -0.09
    flo
    -0.09
    AMA
    -0.09
    çijķçĸµ
    -0.08
     бил
    -0.08
    è´´
    -0.08
    æĮ½æķij
    -0.08
    POSITIVE LOGITS
    åıĪ好
    0.09
    èĸ¤
    0.09
    çijĹ
    0.09
    ä»ĸæĽ¾
    0.09
    æĺİæĻ°
    0.09
    ationally
    0.09
    æĽ´è¦ģ
    0.09
    äºĮèĢħ
    0.08
    èĩªæľī
    0.08
    ä¸ĢçĽ´æ²¡æľī
    0.08
    Activations Density 0.047%

    No Known Activations