© 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. 62025
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
    ä¸Ńå°ıåѦ
    -0.09
    iform
    -0.09
    ä¼ĺ
    -0.08
    eway
    -0.08
    apos
    -0.08
    opl
    -0.08
    åľ°åĮºçļĦ
    -0.08
    ajs
    -0.08
     sounding
    -0.08
    ç®Ģæĺĵ
    -0.08
    POSITIVE LOGITS
     associated
    0.16
    associated
    0.14
    ä¼´éļı
    0.13
    缸åºĶ
    0.13
     Associated
    0.12
    对åºĶçļĦ
    0.12
    ä¼´éļıçĿĢ
    0.12
    缸åºĶçļĦ
    0.11
    Associated
    0.11
     corresponding
    0.10
    Activations Density 0.316%

    No Known Activations