© 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. 26507
    Prev
    Next
    INDEX
    Explanations

    added to

    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
    æ£ł
    -0.08
    åıĪ好
    -0.08
    ship
    -0.08
    ä¿®åħ»
    -0.08
    ifer
    -0.08
    åıĸåĩº
    -0.08
    dma
    -0.08
    .dict
    -0.08
    æĭ¿èµ·
    -0.08
    èµĽ
    -0.08
    POSITIVE LOGITS
    æ¯ıä¸Ģ
    0.10
    ä¸Ĭè°ĥ
    0.09
    ppers
    0.09
    ORED
    0.09
    iffin
    0.09
    oui
    0.09
    æķ°åįĥ
    0.08
    eno
    0.08
    æ´»çĿĢ
    0.08
    åIJİåĨį
    0.08
    Activations Density 0.094%

    No Known Activations