© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40097
    Prev
    Next
    INDEX
    Explanations

    tone, stress, and inflection

    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¸įèĤ¯
    -0.11
    é£İæ°Ķ
    -0.09
    çĦĸ
    -0.09
    ä¹łè¿ij
    -0.08
    辫
    -0.08
    è¿Ļè¾¹
    -0.08
    æĵįåľº
    -0.08
     ChÃŃ
    -0.08
    丢
    -0.08
    anonymous
    -0.08
    POSITIVE LOGITS
    è¯Ńæ°Ķ
    0.16
    表æĥħ
    0.10
    è¯ŃéŁ³
    0.10
    åĮħ容
    0.10
    å£°éŁ³
    0.10
    inton
    0.10
    为åĩĨ
    0.10
    çĶµè¯Ŀ
    0.10
    voices
    0.09
     голоÑģ
    0.09
    Activations Density 0.023%

    No Known Activations