© 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. 2563
    Prev
    Next
    INDEX
    Explanations

    yet, but, and

    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
    紧缺
    -0.10
    èµ·æĿ¥äºĨ
    -0.10
    缺失
    -0.10
    èµ·æĿ¥
    -0.10
    ackers
    -0.09
    çĶŁçĶŁ
    -0.09
    ICO
    -0.09
    ä¸įæ¸ħ
    -0.09
    .Compose
    -0.09
    ement
    -0.09
    POSITIVE LOGITS
    ãģĿãĤĮãģ§ãĤĤ
    0.14
    æĺ¯åĽłä¸º
    0.10
    主è¦ģåİŁåĽł
    0.09
    åİŁåĽł
    0.09
     yet
    0.09
    æĮ«
    0.09
    ä½Ĩå¦Ĥæŀľ
    0.08
    çļĦåİŁåĽł
    0.08
    åıįèĢĮ
    0.08
    yet
    0.08
    Activations Density 0.151%

    No Known Activations