© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33838
    Prev
    Next
    INDEX
    Explanations

    numbers separated by commas

    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
    rzy
    -0.08
    禳
    -0.08
    IDER
    -0.08
    plex
    -0.08
    身亡
    -0.08
    9
    -0.08
    å¹´ç»Ī
    -0.08
     thiá»ĩt
    -0.08
     fin
    -0.08
    åħīå½±
    -0.08
    POSITIVE LOGITS
    éļıæŶéļı
    0.09
    é½IJ
    0.09
    伧
    0.09
    åį°èĬ±
    0.09
     Hut
    0.09
     ÑĢеж
    0.09
    é½Ĭ
    0.09
    (SE
    0.09
    åĸľçĪ±
    0.09
    åij²
    0.08
    Activations Density 0.240%

    No Known Activations