© 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. 29406
    Prev
    Next
    INDEX
    Explanations

    bursts with

    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
    resse
    -0.09
    ago
    -0.08
    Ñģ
    -0.08
    itr
    -0.08
    exus
    -0.08
    è¢ħ
    -0.08
    em
    -0.08
    妹åŃIJ
    -0.08
    herent
    -0.08
    thic
    -0.08
    POSITIVE LOGITS
    ingly
    0.15
    ness
    0.14
    iveness
    0.12
    inel
    0.12
    ible
    0.11
    idon
    0.11
    tings
    0.11
    ties
    0.10
    aneous
    0.10
    iful
    0.10
    Activations Density 0.006%

    No Known Activations