© 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. 29945
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
    âĸ»
    -0.09
    lew
    -0.09
    erving
    -0.09
    ucas
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    山顶
    -0.09
    uspend
    -0.09
    ä¸ĢçĶŁ
    -0.09
    rust
    -0.09
    æ°¸è¿ľ
    -0.09
    POSITIVE LOGITS
    aster
    0.08
     council
    0.08
     меÑĢопÑĢи
    0.08
    ãĤµãĥ©
    0.08
    andel
    0.08
     latter
    0.07
    大äºĭ
    0.07
    çIJĨäºĭä¼ļ
    0.07
    çŃij
    0.07
    å¥İ
    0.07
    Activations Density 0.028%

    No Known Activations