© 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. 49347
    Prev
    Next
    INDEX
    Explanations

    lost 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
    ure
    -0.10
    ä¸įæ¸ħ
    -0.09
    ienes
    -0.09
    ills
    -0.09
    åĩºèĩª
    -0.08
    ä¸įå®ľ
    -0.08
    enic
    -0.08
    çľĭçĤ¹
    -0.08
    asers
    -0.08
    maal
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀè¯Ń
    0.10
    æĭ¢
    0.10
    gether
    0.09
    éĢł
    0.09
    饴
    0.09
    å¾·å°Ķ
    0.09
    ège
    0.09
    ç±³ç²ī
    0.09
    çi
    0.08
    æĪIJéķ¿ä¸º
    0.08
    Activations Density 0.013%

    No Known Activations