© 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. 38965
    Prev
    Next
    INDEX
    Explanations

    comfort zone

    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
    æIJħ
    -0.09
    æĶ¶æĭ¾
    -0.09
    æ±Łæ¹ĸ
    -0.08
    åĢ¼å¾Ĺåħ³æ³¨
    -0.08
    ç«
    -0.08
    åĩī
    -0.08
    åIJ¦
    -0.08
    æIJŃ
    -0.08
    éĢĦ
    -0.08
    колÑĮ
    -0.08
    POSITIVE LOGITS
    èĪĴéĢĤ
    0.16
    åģľçķĻåľ¨
    0.15
    èĪĴéĢĤçļĦ
    0.14
     Comfort
    0.12
    çĨŁæĤīçļĦ
    0.12
    åĽºå®ļçļĦ
    0.12
    åĽºå®ļ
    0.12
    å±ĢéĻIJäºİ
    0.11
     spoon
    0.11
     comfortable
    0.11
    Activations Density 0.091%

    No Known Activations