© 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. 6427
    Prev
    Next
    INDEX
    Explanations

    scientific names of species

    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
    cth
    -0.08
    ÑĢоÑģÑĤ
    -0.08
    _BUFFER
    -0.08
    ög
    -0.08
    æ·¡æ·¡
    -0.08
     âĨĵ
    -0.07
    GBK
    -0.07
    nga
    -0.07
    REW
    -0.07
    çł
    -0.07
    POSITIVE LOGITS
    ä»Ĭ天æĪij们
    0.10
    æĪij们就
    0.09
    ä»Ģä¹Īåij¢
    0.09
    ä¸ľè¥¿
    0.09
    å¦ĤæŀľæĪij们
    0.09
    æ¼Ķèīº
    0.09
    ä½ĨæĪij们
    0.09
    æĿ°åĩº
    0.09
     spp
    0.09
    æĿĤ
    0.09
    Activations Density 0.228%

    No Known Activations