© 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. 56636
    Prev
    Next
    INDEX
    Explanations

    appetite and hunger

    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
    æĺİæ¸ħ
    -0.09
    çĽ´è¾¾
    -0.08
    æĻ®åıĬ
    -0.08
    翻身
    -0.08
    车åĨħ
    -0.08
    åĻ¼
    -0.08
    车åŃIJ
    -0.08
    æĭ¯
    -0.08
     íĶ¼íķ´
    -0.08
     Cave
    -0.08
    POSITIVE LOGITS
    é£Łæ¬²
    0.22
     appetite
    0.21
    èĥĥåı£
    0.19
     Appet
    0.16
    é£Ł
    0.12
    é¥Ń
    0.12
     vor
    0.12
    饥
    0.11
     appet
    0.11
     hunger
    0.11
    Activations Density 0.081%

    No Known Activations