© 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. 29377
    Prev
    Next
    INDEX
    Explanations

    any kind

    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
    ä¸įå¿į
    -0.11
     facto
    -0.10
     hẳn
    -0.09
     вÑģего
    -0.09
    locked
    -0.09
    iously
    -0.09
    æį¢åıĸ
    -0.09
    åİŁè°ħ
    -0.09
    ious
    -0.09
    ploy
    -0.09
    POSITIVE LOGITS
    à¹Į
    0.13
    ê¹IJ
    0.10
    íģ¼
    0.10
    ugen
    0.09
    اء
    0.08
    棹
    0.08
    âĻĤ
    0.08
    desk
    0.08
    ish
    0.08
    oret
    0.08
    Activations Density 0.063%

    No Known Activations