© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51860
    Prev
    Next
    INDEX
    Explanations

    fragrance

    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
    伤çĹħ
    -0.10
    èľ©
    -0.09
    æĢĢæĬ±
    -0.09
    éĺ´å½±
    -0.08
    æĸ°éĹ»è®°èĢħ
    -0.08
    æīĵçł´äºĨ
    -0.08
    åIJĥ饱
    -0.08
    åļİ
    -0.08
    éĤ£ä½į
    -0.08
    é¬ĥ
    -0.08
    POSITIVE LOGITS
    åĹħ
    0.12
    çĨı
    0.11
     пÑĢиÑıÑĤ
    0.10
    é¦Ļ
    0.10
     fragrance
    0.10
    馥
    0.10
     Frag
    0.10
    frag
    0.09
    дÑĥÑĪ
    0.09
    空éĹ´
    0.09
    Activations Density 0.037%

    No Known Activations