© 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. 8666
    Prev
    Next
    INDEX
    Explanations

    satisfaction and pleasure

    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
    宾客
    -0.10
    å®īåħ¨éļIJæĤ£
    -0.10
    å°ıå¿ĥ翼翼
    -0.09
    éħ½
    -0.09
    åĬłç´§
    -0.09
    åĭī强
    -0.09
    客åķĨ
    -0.09
    å¾Ģ
    -0.09
    åĽĽå¤Ħ
    -0.09
    ç¯ĵ
    -0.09
    POSITIVE LOGITS
     satisfaction
    0.12
    æĪIJå°±æĦŁ
    0.11
    满足
    0.11
    çĪ½
    0.11
     Satisfaction
    0.11
    æħ°
    0.11
    æĢ¡
    0.10
    atisfaction
    0.10
     satisfying
    0.10
     pleasure
    0.09
    Activations Density 0.088%

    No Known Activations