© 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. 51299
    Prev
    Next
    INDEX
    Explanations

    subjective experience and feelings

    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
     зав
    -0.10
    tern
    -0.08
     Crazy
    -0.08
    евиÑĩ
    -0.08
    ä¸Ģ对
    -0.08
     Perf
    -0.08
    _util
    -0.08
    çĪ¹
    -0.08
     Clothes
    -0.07
    讲
    -0.07
    POSITIVE LOGITS
    ä½ĵéªĮ
    0.13
     experience
    0.12
    experience
    0.11
    é«Ķé©Ĺ
    0.11
    æĦŁåıĹåĪ°
    0.10
    Experience
    0.10
    èĬ±èįī
    0.10
    åħ³äºİæĪij们
    0.10
    çļĦæĦŁè§ī
    0.10
    çľ¼åīįçļĦ
    0.10
    Activations Density 0.107%

    No Known Activations