© 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. 31494
    Prev
    Next
    INDEX
    Explanations

    eating choices and diet

    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
    èĴ²
    -0.10
    éĵ¤
    -0.09
    AZY
    -0.09
    对åŃ©åŃIJ
    -0.09
    åįľ
    -0.09
    èĽī
    -0.08
    æ°Ķæ°Ľ
    -0.08
    èĦ±
    -0.08
    çĽ¸äº²
    -0.08
    uname
    -0.08
    POSITIVE LOGITS
     ed
    0.10
     macro
    0.09
    7
    0.08
    æĶĿ
    0.08
    çļĦçŁ¥è¯Ĩ
    0.08
     tro
    0.08
    8
    0.08
    ê°Ŀ
    0.08
     balanced
    0.08
     detail
    0.08
    Activations Density 0.031%

    No Known Activations