© 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. 11928
    Prev
    Next
    INDEX
    Explanations

    diaphragmatic

    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
    åĻ¨æĿIJ
    -0.10
    åIJĪè§Ħ
    -0.09
    æī¹è¯Ħ
    -0.09
    çħ§æł·
    -0.09
    âĦħ
    -0.08
    表æī¬
    -0.08
    ingo
    -0.08
    ç¤ģ
    -0.08
    çłij
    -0.08
    æĥħ
    -0.08
    POSITIVE LOGITS
     Caf
    0.10
     تÙħاÙħ
    0.09
    pery
    0.09
    .vm
    0.09
    ustin
    0.08
     beh
    0.08
    æĴij
    0.08
    ulg
    0.08
    ç¼ij
    0.08
    mdl
    0.08
    Activations Density 0.042%

    No Known Activations