© 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. 62176
    Prev
    Next
    INDEX
    Explanations

    materials, entities

    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
    äºĶ大
    -0.10
    ä¸Ģ大åłĨ
    -0.10
    ä¸Ńæ¯Ĵ
    -0.10
    æĿĢæīĭ
    -0.10
    .ep
    -0.09
    大å¦Ī
    -0.09
    apult
    -0.09
    .opensource
    -0.08
    Void
    -0.08
    pedo
    -0.08
    POSITIVE LOGITS
    夹
    0.09
     inters
    0.08
     presumably
    0.08
     interes
    0.08
    æĦŁåħ´è¶£çļĦ
    0.08
     possibly
    0.07
    lags
    0.07
     sympath
    0.07
    åħ·æľīä¸Ģå®ļ
    0.07
    Beat
    0.07
    Activations Density 0.101%

    No Known Activations