© 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. 63262
    Prev
    Next
    INDEX
    Explanations

    columnists and authors

    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
    ÙĬات
    -0.09
    ãģĮãģĭ
    -0.08
    è¦ĨçĽĸçİĩ
    -0.08
    å·§
    -0.08
    _sink
    -0.08
    éĴĪ对
    -0.08
    æĭĸ延
    -0.08
    era
    -0.08
    åıijå±ķ空éĹ´
    -0.08
    ино
    -0.08
    POSITIVE LOGITS
     gá»įn
    0.09
    çĽ²
    0.09
    .fixture
    0.09
     nghiá»ĩm
    0.08
    .Signal
    0.08
    妥
    0.08
    ä¹ħäºĨ
    0.08
    è¿Ļç±»
    0.08
     Midwest
    0.08
    åŃľ
    0.08
    Activations Density 0.041%

    No Known Activations