© 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. 33825
    Prev
    Next
    INDEX
    Explanations

    past role or state

    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
    èĢģ人家
    -0.10
    èĢģ人
    -0.09
    è·Łä»ĸ
    -0.09
    reopen
    -0.09
    è¿ĻäºĽäºº
    -0.09
    reb
    -0.08
    å¨ģ
    -0.08
    ä¹°ä¸ľè¥¿
    -0.08
    regs
    -0.08
    PAD
    -0.08
    POSITIVE LOGITS
    ä¸Ģ大
    0.10
    åĢĻ
    0.09
    èĵį
    0.09
    èĭ±æł¼
    0.09
    éĻIJå®ļ
    0.09
    blr
    0.09
     NEO
    0.08
    oard
    0.08
    inate
    0.08
    åħ¼
    0.08
    Activations Density 0.095%

    No Known Activations