© 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. 31683
    Prev
    Next
    INDEX
    Explanations

    world's

    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
    åij¨åĽ´çļĦ
    -0.10
    æĤ¸
    -0.09
    ä¼¼
    -0.09
    obody
    -0.09
    5
    -0.08
    åħ¨ä½ĵåijĺå·¥
    -0.08
    åij¨åĽ´
    -0.08
    å¹ħ
    -0.08
    0
    -0.08
    çĩĥ
    -0.08
    POSITIVE LOGITS
    izr
    0.09
    滹
    0.09
    ä¸ĵä¸ļåĮĸ
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.08
    currentTime
    0.08
    ðŁĮİ
    0.08
    缯
    0.08
    _DISPATCH
    0.08
    temps
    0.08
    hart
    0.08
    Activations Density 0.029%

    No Known Activations