© 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. 54987
    Prev
    Next
    INDEX
    Explanations

    stock ticker codes

    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
    reh
    -0.09
    æį©
    -0.08
    ÑģÑĤи
    -0.08
     çek
    -0.08
    åħħ
    -0.08
    ing
    -0.08
    çļĦå°±æĺ¯
    -0.08
    åī
    -0.08
    Permissions
    -0.08
    ider
    -0.07
    POSITIVE LOGITS
    ä¸¤å¼ł
    0.10
    washer
    0.09
    é¹Ī
    0.09
    大éĻĨ
    0.08
    igli
    0.08
    éĹ»
    0.08
    秦
    0.08
    MAX
    0.08
    oe
    0.08
    åĵī
    0.08
    Activations Density 0.016%

    No Known Activations