© 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. 2414
    Prev
    Next
    INDEX
    Explanations

    feeling of comfort

    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
    ä¸ĭ乡
    -0.09
    åıĭæĥħ
    -0.09
    ha
    -0.09
    çĿ¥
    -0.08
    fos
    -0.08
    çī¹æĦı
    -0.08
    æĸĹå¿Ĺ
    -0.08
    宿
    -0.08
    åij½è¿IJ
    -0.08
    åIJ¸çº³
    -0.08
    POSITIVE LOGITS
    èĪĴéĢĤ
    0.16
    èĪĴéĢĤçļĦ
    0.12
     discomfort
    0.12
     Comfort
    0.12
    Comfort
    0.12
     комÑĦоÑĢÑĤ
    0.11
     comfort
    0.11
    comfort
    0.11
    ä¸įèĪĴæľį
    0.11
     comfortable
    0.11
    Activations Density 0.034%

    No Known Activations