© 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. 31543
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    zen
    -0.10
    çĶļèĩ³
    -0.10
    nable
    -0.08
     Wire
    -0.08
     xuyên
    -0.08
    2
    -0.08
     Wired
    -0.08
    isplay
    -0.08
    ала
    -0.08
    1
    -0.08
    POSITIVE LOGITS
    æĸ°å±ĢéĿ¢
    0.11
    ä¸įæĺ¯ä¸Ģ个
    0.10
    è¿ĻäºĽä¸ľè¥¿
    0.10
    ä¸įä»ħæĺ¯
    0.10
    ä»Ģä¹Īä¸ľè¥¿
    0.10
    çĤ¹å¤ļ
    0.10
    ä»Ģä¹Īåij¢
    0.10
    .epoch
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    ä¸įä»ħä»ħæĺ¯
    0.09
    Activations Density 0.050%

    No Known Activations