© 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. 10197
    Prev
    Next
    INDEX
    Explanations

    check and ensure

    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
     Bite
    -0.09
    纯åĩĢ
    -0.09
    æİ¥åĪ°
    -0.08
     gon
    -0.08
     re
    -0.08
     vi
    -0.08
    atural
    -0.08
    æijģ
    -0.08
    çIJ¨
    -0.08
    ä½łå¥½
    -0.08
    POSITIVE LOGITS
    lama
    0.10
    æľĢæĸ°
    0.09
    å°ļ
    0.09
    aho
    0.09
    arl
    0.09
    åĩĨç¡®
    0.09
    é£İåIJ¹
    0.09
    edor
    0.08
    _Params
    0.08
    _REQUIRE
    0.08
    Activations Density 0.041%

    No Known Activations