© 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. 51756
    Prev
    Next
    INDEX
    Explanations

    to introduce explanations

    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
    红åĪ©
    -0.10
    ogne
    -0.10
    ç»°
    -0.10
    _aug
    -0.09
     GANG
    -0.09
    ducation
    -0.09
    éĤĪ
    -0.09
    庶
    -0.09
    FRING
    -0.09
    ç¬ĭ
    -0.09
    POSITIVE LOGITS
    æĪij家
    0.09
    åı¦ä¸Ģ个
    0.08
     SOM
    0.08
    åĢŁçĶ¨
    0.08
     another
    0.08
    ä¸Ģåı¥è¯Ŀ
    0.08
     Maurice
    0.08
    0
    0.08
    æĪijçļĦ
    0.08
    nod
    0.08
    Activations Density 0.026%

    No Known Activations