© 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. 26373
    Prev
    Next
    INDEX
    Explanations

    among them

    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
    OTHER
    -0.10
    éĬ®
    -0.10
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    åı¦å¤ĸ
    -0.09
     дÑĢÑĥгой
    -0.09
    åħ¶ä»ĸ
    -0.09
    eting
    -0.09
    åĨįè§ģ
    -0.08
    regs
    -0.08
    ä»»ä½ķå½¢å¼ı
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.22
    æ¯Ķå¦Ĥ
    0.20
    æ¯Ķå¦Ĥ说
    0.18
    ä¾ĭå¦Ĥ
    0.18
    诸å¦Ĥ
    0.17
    èѬå¦Ĥ
    0.15
    ä¾ĭãģĪãģ°
    0.15
     ones
    0.13
     ÐĿапÑĢимеÑĢ
    0.13
    åĮħæĭ¬
    0.13
    Activations Density 0.383%

    No Known Activations