© 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. 60916
    Prev
    Next
    INDEX
    Explanations

    open and closed status

    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
    ä¸Ģ个éĹ®é¢ĺ
    -0.11
    ä¸įæĸŃæī©å¤§
    -0.11
    æĢ»éĺŁ
    -0.10
    èĹķ
    -0.09
    åĬ£
    -0.09
    æ¶ķ
    -0.09
    åİĦ
    -0.09
    æ©IJ
    -0.09
    滥
    -0.09
     Isabel
    -0.08
    POSITIVE LOGITS
    åħ³éĹŃ
    0.13
    åħ³éŨ
    0.11
     shutter
    0.11
    æŃĩ
    0.11
    éĹŃ
    0.10
     shut
    0.10
     Closed
    0.10
    å¼ĢéŨ
    0.10
    ä¸ĬçıŃ
    0.09
    Closure
    0.09
    Activations Density 0.074%

    No Known Activations