© 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. 47734
    Prev
    Next
    INDEX
    Explanations

    references to options or locations

    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
    ç©¿
    -0.10
    interrupt
    -0.09
    inus
    -0.08
    .cleanup
    -0.08
    nut
    -0.08
    dana
    -0.08
    iem
    -0.08
     jer
    -0.08
    _unused
    -0.08
    æĶ»
    -0.08
    POSITIVE LOGITS
    说åĩºæĿ¥
    0.11
    交éĢļå·¥åħ·
    0.11
    æ¹¾
    0.10
    èŁł
    0.10
    ä¸Ńæĸ¹
    0.10
    ä»Ĩ
    0.10
    æĪijæīį
    0.10
    ç¥ĸçĪ¶
    0.10
    æĶ¹éĿ©åĪĽæĸ°
    0.09
    åĪ°è¿ĻéĩĮ
    0.09
    Activations Density 0.011%

    No Known Activations