© 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. 50298
    Prev
    Next
    INDEX
    Explanations

    construction workers

    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
    çĭ©
    -0.12
    æĶ¹éĢł
    -0.09
     jug
    -0.09
    èĮ¸
    -0.09
    缫
    -0.09
    ä¸Ģåı£æ°Ķ
    -0.09
    çĽ¸äº²
    -0.08
    椰
    -0.08
    .ny
    -0.08
    åı¯çĸij
    -0.08
    POSITIVE LOGITS
    å·¥åľ°
    0.18
    æĸ½å·¥çİ°åľº
    0.16
    æĸ½å·¥
    0.16
    ä¸ļ主
    0.13
    çĽijçIJĨ
    0.13
    è¿Ľåľº
    0.13
    çİ°åľº
    0.12
    åľ¨çİ°åľº
    0.12
    å·¥æľŁ
    0.12
    åľŁ
    0.11
    Activations Density 0.116%

    No Known Activations