© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36450
    Prev
    Next
    INDEX
    Explanations

    word document files

    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
    athed
    -0.09
    оÑģÑĮ
    -0.09
    è¿ŀ线
    -0.09
    ario
    -0.09
    两个人
    -0.09
    çĻŀ
    -0.09
    .uml
    -0.09
    éĵ²
    -0.08
    ected
    -0.08
    夷
    -0.08
    POSITIVE LOGITS
     Word
    0.09
    åºĶèģĺ
    0.09
    åį°åıij
    0.09
    æ¡£
    0.08
    åŃļ
    0.08
    æĽ·
    0.08
    åħ¬åħ³
    0.08
    æĸĩæ¡£
    0.08
    (writer
    0.08
    åĬŀåħ¬
    0.08
    Activations Density 0.089%

    No Known Activations