© 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. 61549
    Prev
    Next
    INDEX
    Explanations

    skin aging and wrinkles

    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
    å²Ļ
    -0.11
    æIJĶ
    -0.11
    itan
    -0.10
    åªĴ
    -0.09
    æĶ¹éĿ©åĪĽæĸ°
    -0.09
    éĥ½æĥ³
    -0.09
    æģģ
    -0.09
    带ç»Ļ
    -0.09
    å«īå¦Ĵ
    -0.08
    åı¯æĥ³
    -0.08
    POSITIVE LOGITS
    ละ
    0.09
    æĦ¿
    0.09
    .lesson
    0.09
    æ®·
    0.09
    ixin
    0.09
    enia
    0.09
    åĮºåĨħ
    0.08
     inconvenient
    0.08
    åĪ½
    0.08
    presso
    0.08
    Activations Density 0.007%

    No Known Activations