© 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. 10631
    Prev
    Next
    INDEX
    Explanations

    service

    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
    æł·çļĦ
    -0.12
    çĦ¶æĺ¯
    -0.12
    ervices
    -0.11
    å±±åºĦ
    -0.10
    峡
    -0.10
    ä»Ģä¹Īä¸ľè¥¿
    -0.10
    çĹĩ
    -0.10
    ãĤ¤ãĥĪ
    -0.10
    ervice
    -0.10
    å±ij
    -0.09
    POSITIVE LOGITS
    æıIJä¾ĽåķĨ
    0.12
    fully
    0.10
    ookie
    0.09
    abled
    0.09
    esta
    0.09
    zed
    0.09
    .UserService
    0.09
    ful
    0.09
    able
    0.09
    èĩ³ä¸Ĭ
    0.09
    Activations Density 0.095%

    No Known Activations