© 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. 64091
    Prev
    Next
    INDEX
    Explanations

    declarative language

    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
    Negative Logits
    atk
    -0.09
    fä
    -0.08
     Sat
    -0.08
    åħ¬çĶ¨
    -0.08
     sat
    -0.08
    çļĦçĪ¶äº²
    -0.08
    éĩįä¸Ń
    -0.08
    å·¥ä½ľçļĦ
    -0.08
    -prepend
    -0.08
    åIJ«
    -0.08
    POSITIVE LOGITS
     declar
    0.10
    Lights
    0.09
    ä¸ĢéŨ
    0.09
    è§ĦåĪĻ
    0.09
    缩
    0.09
    åij½ä»¤
    0.08
    urable
    0.08
    æŀĦæĢĿ
    0.08
    èĦ±è´«èĩ´å¯Į
    0.08
    uct
    0.08
    Activations Density 0.357%

    No Known Activations