© 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. 10532
    Prev
    Next
    INDEX
    Explanations

    rewarding feeling or outcome

    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
    AVIS
    -0.09
    天涯
    -0.09
     situ
    -0.09
    çļĦä¹łæĥ¯
    -0.09
    iscrim
    -0.08
    abis
    -0.08
    è¿Ļæł·ä¸Ģ
    -0.08
    æķĻãģĪ
    -0.08
    æīĵæī°
    -0.08
    赶赴
    -0.08
    POSITIVE LOGITS
    æĪIJå°±æĦŁ
    0.16
    æĪIJæŀľ
    0.14
    æĶ¶èİ·
    0.13
    èĩªè±ª
    0.13
    欣æħ°
    0.11
     pride
    0.10
    æĶ»åħĭ
    0.10
    _reward
    0.10
    丰æĶ¶
    0.10
    åħĭæľį
    0.10
    Activations Density 0.047%

    No Known Activations