© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    this time around

    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
    èµ·æĿ¥äºĨ
    -0.09
    iasi
    -0.09
    ERA
    -0.09
    PLACE
    -0.09
    oment
    -0.09
    å¤ĸåĩº
    -0.08
    è¿Ļæīįæĺ¯
    -0.08
    ç£IJ
    -0.08
    adic
    -0.08
    æľīå¾ħ
    -0.08
    POSITIVE LOGITS
    led
    0.09
    rawer
    0.09
     Sud
    0.08
    ution
    0.08
    ä¸ķ
    0.08
     możemy
    0.08
    åŁºæķ°
    0.08
    æ±Ĥå©ļ
    0.08
    lege
    0.08
    æ±ŁåĮº
    0.08
    Activations Density 0.003%

    No Known Activations