© 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. 38765
    Prev
    Next
    INDEX
    Explanations

    countries and residency

    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
    ettes
    -0.10
    è¿IJåĬ¨
    -0.09
    istrar
    -0.09
    .Params
    -0.08
    able
    -0.08
    æķijåij½
    -0.08
     Nex
    -0.08
    iÃŁ
    -0.08
    帽
    -0.08
     ÑĥÑģл
    -0.08
    POSITIVE LOGITS
    é£İåIJ¹
    0.10
    ayah
    0.10
    ä¸įåľ¨
    0.10
    çŀ»
    0.10
    CharCode
    0.10
    æĥĨ
    0.09
    峪
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
     Blanch
    0.09
    çĮľ
    0.09
    Activations Density 0.047%

    No Known Activations