© 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. 53865
    Prev
    Next
    INDEX
    Explanations

    food intake

    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
    ister
    -0.10
    åħij
    -0.09
     Blonde
    -0.09
    æĪ¾
    -0.09
    èĭ£
    -0.08
    ISTER
    -0.08
    æīĵåĩ»
    -0.08
    ÑģÑĤеÑĢ
    -0.08
    è½²
    -0.08
    å´©æºĥ
    -0.08
    POSITIVE LOGITS
    饥饿
    0.20
    åIJĥ饱
    0.17
    饥
    0.17
    饱
    0.16
    饿
    0.15
     hunger
    0.14
    è¿Ľé£Ł
    0.13
     hungry
    0.13
    é£Łæ¬²
    0.13
    饫
    0.13
    Activations Density 0.174%

    No Known Activations