© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59082
    Prev
    Next
    INDEX
    Explanations

    text generation

    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
    æĭ¯
    -0.13
    èĨĤ
    -0.11
    orage
    -0.10
    åĽłåľ°
    -0.09
    åıĭåĸĦ
    -0.09
    åĴĮæĬĢæľ¯
    -0.09
    æ°¸ä¹ħ
    -0.09
    解åĨ³éĹ®é¢ĺ
    -0.09
    æĬĵç´§
    -0.09
    æĢĢæĬ±
    -0.09
    POSITIVE LOGITS
    产åĩº
    0.10
    lier
    0.09
    ä½ľåĵģ
    0.09
    åıijçĶµ
    0.09
    åIJŃ
    0.09
    çĤī
    0.08
    ajan
    0.08
    åĪĽä½ľ
    0.08
    æľīä¸Ģå®ļçļĦ
    0.08
    _permalink
    0.08
    Activations Density 0.032%

    No Known Activations