© 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. 29956
    Prev
    Next
    INDEX
    Explanations

    pleasant or unpleasant feeling

    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
    榷
    -0.10
    rah
    -0.09
    è¿Ļæł·æīįèĥ½
    -0.09
     Gree
    -0.08
    elve
    -0.08
    好象
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    æĽ´å¥½åľ°
    -0.08
    ioni
    -0.08
    /single
    -0.08
    POSITIVE LOGITS
     пÑĢиÑıÑĤ
    0.11
    æĦī
    0.11
    èĪĴéĢĤ
    0.10
    å¼ĤæĢ§
    0.10
     pleasant
    0.10
    lü
    0.10
     agréable
    0.10
    å¼Ģ端
    0.10
    èĪĴéĢĤçļĦ
    0.09
    åħīéĺ´
    0.09
    Activations Density 0.034%

    No Known Activations