© 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. 3542
    Prev
    Next
    INDEX
    Explanations

    food and meals

    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
    é¼¹
    -0.10
    _callable
    -0.09
    modx
    -0.08
    æĸĩåĮĸéģĹ产
    -0.08
    ôle
    -0.08
     Teddy
    -0.08
    åł¤
    -0.08
    纩
    -0.08
    rike
    -0.08
    éĺ²
    -0.08
    POSITIVE LOGITS
    åĬłå¿«æİ¨è¿Ľ
    0.10
    uj
    0.09
    æ¯įæł¡
    0.09
    overn
    0.09
    ness
    0.09
    æĿ¥çĶµ
    0.08
    itos
    0.08
    ÑĢоÑģ
    0.08
    поÑĤ
    0.08
    olib
    0.08
    Activations Density 0.012%

    No Known Activations