© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53239
    Prev
    Next
    INDEX
    Explanations

    octopus

    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
    åİ»åĵªåĦ¿
    -0.10
    æķ´ä¸ªäºº
    -0.10
    ppy
    -0.09
    .sales
    -0.09
    iry
    -0.09
    èijµ
    -0.09
    çĶľ
    -0.09
    avian
    -0.09
    åĴ¯
    -0.09
    çļĦ人çī©
    -0.08
    POSITIVE LOGITS
    æijŃ
    0.11
    éĹ¯
    0.10
    éŁ
    0.09
    çĿĢçľ¼
    0.09
    大èĥĨ
    0.09
    smarty
    0.09
    æĵ¢
    0.09
     Ink
    0.08
    aled
    0.08
    墨
    0.08
    Activations Density 0.047%

    No Known Activations