© 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. 30381
    Prev
    Next
    INDEX
    Explanations

    label or title

    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
    IRO
    -0.09
    едÑĮ
    -0.08
    alth
    -0.08
    udu
    -0.08
    arin
    -0.08
    æĦıåĽ¾
    -0.08
    AIL
    -0.08
    æŀĭ
    -0.08
    å®Īä½ı
    -0.08
    phin
    -0.08
    POSITIVE LOGITS
    æłĩçŃ¾
    0.13
    çļĦ身份
    0.11
     label
    0.11
    label
    0.10
    绨
    0.10
    (labels
    0.10
     labels
    0.10
    çĥĻ
    0.10
    (label
    0.09
    称åı·
    0.09
    Activations Density 0.210%

    No Known Activations