© 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. 30641
    Prev
    Next
    INDEX
    Explanations

    FIG. 1, 2, 3, 8, 101 or 201

    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
    æĭIJ
    -0.10
    çŃĭ
    -0.09
    axter
    -0.09
    .ua
    -0.09
     Slee
    -0.09
     Bomb
    -0.09
    覺å¾Ĺ
    -0.08
    èļķ
    -0.08
    acos
    -0.08
    ìĬ¬
    -0.08
    POSITIVE LOGITS
    人éĢī
    0.10
    بار
    0.09
    éķĬ
    0.09
    imizer
    0.08
    èĬ³é¦Ļ
    0.08
    å¾Ģåīį
    0.08
    rais
    0.08
    ig
    0.08
    æĬķèµĦé¢Ŀ
    0.08
    òn
    0.08
    Activations Density 0.136%

    No Known Activations