© 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. 55922
    Prev
    Next
    INDEX
    Explanations

    easy to use

    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
    fel
    -0.09
    asc
    -0.09
     اÙĦÙħزÙĬد
    -0.08
    rush
    -0.08
    è¯ķåĽ¾
    -0.08
    nd
    -0.08
    æĽ´éĢĤåIJĪ
    -0.07
    ican
    -0.07
     inability
    -0.07
     bist
    -0.07
    POSITIVE LOGITS
    æ¡¢
    0.11
    驾é©Ń
    0.11
    çľĭåĩº
    0.11
    è¿Ľåıĸ
    0.10
    unner
    0.10
    éħįä¸Ĭ
    0.10
    éĢīæĭ
    0.10
    ONS
    0.09
    éķ¿å¤§
    0.09
    åıĸèĥľ
    0.09
    Activations Density 0.026%

    No Known Activations