© 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. 26171
    Prev
    Next
    INDEX
    Explanations

    risk and complexity involved

    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
    çĪ°
    -0.11
    eries
    -0.10
    .stamp
    -0.10
    ÑģÑĤвенно
    -0.09
    åĶĨ
    -0.09
    ا
    -0.09
    没æĥ³åĪ°
    -0.09
    éĺĬ
    -0.09
    lime
    -0.09
    æĥ³è¿ĩ
    -0.09
    POSITIVE LOGITS
    åĪ°äºĨ
    0.09
    ä¸Ģå®ļæĺ¯
    0.09
    agna
    0.08
    elder
    0.08
    ioned
    0.08
    oney
    0.08
    ocked
    0.08
    太å¤ļçļĦ
    0.08
    å
    0.08
    ados
    0.08
    Activations Density 0.049%

    No Known Activations