© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36377
    Prev
    Next
    INDEX
    Explanations

    vanilla and extracts

    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
    éĵĥ
    -0.10
    鸿
    -0.09
     Pell
    -0.09
     Wolff
    -0.09
    ма
    -0.08
    èį¦
    -0.08
    åĿį
    -0.08
    æľįåĬ¡è´¨éĩı
    -0.08
     saturn
    -0.08
    èĦ±èIJ½
    -0.08
    POSITIVE LOGITS
     vanilla
    0.11
     prem
    0.09
     Vanilla
    0.09
    zej
    0.09
    kip
    0.09
    æģ£
    0.08
     tah
    0.08
    ä¸Ģ身
    0.08
    æħ¢
    0.08
    çİ«çij°
    0.08
    Activations Density 0.004%

    No Known Activations