© 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. 58685
    Prev
    Next
    INDEX
    Explanations

    generation / generations

    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
    第äºĮç§į
    -0.09
    ombre
    -0.09
    æĺĻ
    -0.09
    æģģ
    -0.09
    .twig
    -0.09
    istant
    -0.08
    è¡Įä¸ļåıijå±ķ
    -0.08
    åħĪçĶŁ
    -0.08
    uem
    -0.08
    ç¿ħ
    -0.08
    POSITIVE LOGITS
    naire
    0.11
    nal
    0.10
    ally
    0.10
    ä¸ŃæľŁ
    0.10
    ARY
    0.10
    ary
    0.09
    ubby
    0.09
    erb
    0.09
    nelle
    0.09
    以ä¾Ĩ
    0.08
    Activations Density 0.012%

    No Known Activations