© 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. 50991
    Prev
    Next
    INDEX
    Explanations

    more context or information

    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
    å¿«éĢŁåıijå±ķ
    -0.09
     Marion
    -0.09
    ç«Ł
    -0.08
    欲
    -0.08
    æī
    -0.08
    atoi
    -0.08
    æľ
    -0.08
    anship
    -0.08
     borrow
    -0.08
    licer
    -0.08
    POSITIVE LOGITS
    çľĭä¸Ģçľĭ
    0.12
     context
    0.11
    è¹ī
    0.10
    context
    0.10
     tiêu
    0.09
    /context
    0.09
     getContext
    0.09
     contexto
    0.09
     contexts
    0.09
    è¶³å¤ŁçļĦ
    0.09
    Activations Density 0.018%

    No Known Activations