© 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. 40217
    Prev
    Next
    INDEX
    Explanations

    pallet dimensions, ramp, security

    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
    çİ°åĩº
    -0.11
    妥åįı
    -0.10
    毳
    -0.10
    æĸĹäºī
    -0.09
    çij¶
    -0.09
     комиÑģÑģи
    -0.09
    .Raw
    -0.09
    å¹´éĻIJ
    -0.09
    atti
    -0.09
    ấ
    -0.09
    POSITIVE LOGITS
    panic
    0.09
    éĢļåħ³
    0.08
    ograms
    0.08
    çĪ°
    0.08
    大çĪ·
    0.08
     Assembly
    0.08
    éĽĨè£ħç®±
    0.08
    ogram
    0.08
     Bry
    0.08
     Probe
    0.08
    Activations Density 0.116%

    No Known Activations