© 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. 5337
    Prev
    Next
    INDEX
    Explanations

    paper and stock materials

    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
    7
    -0.09
    6
    -0.09
    able
    -0.09
    8
    -0.09
    ç°¸
    -0.08
    3
    -0.08
     Gaul
    -0.08
    椽
    -0.08
    2
    -0.08
     tool
    -0.08
    POSITIVE LOGITS
    两åij¨
    0.10
    åĵĪåĵĪ
    0.09
    æ°ijæĹıæĸĩåĮĸ
    0.09
    ç¼ľ
    0.09
    äºİæĺ¯æĪij
    0.09
    æĺ¯æĪijçļĦ
    0.09
    使çĶ¨æĿĥ
    0.09
    驺
    0.09
    æ¹ľ
    0.09
    ä¸ļ
    0.09
    Activations Density 0.015%

    No Known Activations