© 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. 62089
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
     sed
    -0.09
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    amina
    -0.08
    ç²¾èĭ±
    -0.08
    竦
    -0.07
    彩
    -0.07
    寡
    -0.07
    \Annotation
    -0.07
    bable
    -0.07
    sed
    -0.07
    POSITIVE LOGITS
    ALLE
    0.11
    åĪĨ管
    0.10
    æĽ¾ä»»
    0.10
    æĮĩæľĽ
    0.10
    çĿ£åĬŀ
    0.10
    ä¸Ģä½į
    0.10
    åģļå®Į
    0.09
    åı¦ä¸Ģä½į
    0.09
     Shi
    0.09
    èIJ¥è¿IJ
    0.09
    Activations Density 0.090%

    No Known Activations