© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9794
    Prev
    Next
    INDEX
    Explanations

    hunger satiety fullness

    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
    çĶŁæ´»çݯå¢ĥ
    -0.09
    èij¬
    -0.09
    åıĺæĢģ
    -0.09
    éĵº
    -0.09
    宣
    -0.09
     Marriage
    -0.09
    æ´»
    -0.08
     ìĸ´
    -0.08
    æݨ广
    -0.08
     Forced
    -0.08
    POSITIVE LOGITS
    åIJĥ饱
    0.17
    饱
    0.17
    飽
    0.14
    饿
    0.13
    åħħ足
    0.13
    é¤į
    0.12
    饥饿
    0.12
     hunger
    0.12
    åIJĥå¾Ĺ
    0.12
    èĤļåŃIJ
    0.11
    Activations Density 0.076%

    No Known Activations