© 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. 3696
    Prev
    Next
    INDEX
    Explanations

    pelvic

    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
    ively
    -0.10
    abelle
    -0.09
     nghá»ģ
    -0.09
    볨
    -0.09
    ners
    -0.09
    ammen
    -0.08
     мÑıг
    -0.08
    bearer
    -0.08
    sWith
    -0.08
     Äijáo
    -0.08
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.12
    é¹ķ
    0.11
     dozen
    0.10
    oder
    0.10
    egt
    0.09
    aspers
    0.09
    åĨľä¸ļ大åѦ
    0.09
     cánh
    0.09
    zig
    0.09
    azaar
    0.09
    Activations Density 0.025%

    No Known Activations