© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2770
    Prev
    Next
    INDEX
    Explanations

    hunger and fullness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    _shared
    -0.24
    ctest
    -0.24
    Radio
    -0.23
     radios
    -0.23
    orts
    -0.23
    éĵ¶è¡Įä¸ļ
    -0.22
    åħ¨åĽ½
    -0.22
    åħ«åį¦
    -0.22
     dealings
    -0.22
     dac
    -0.22
    POSITIVE LOGITS
     calorie
    0.36
     hunger
    0.35
    饥饿
    0.34
     calories
    0.32
    é£Łçī©
    0.30
     appetite
    0.29
    饿
    0.28
    åĩıèĤ¥
    0.28
    å¡«åħħ
    0.27
     Calories
    0.27
    Activations Density 0.044%

    No Known Activations