© 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. 33258
    Prev
    Next
    INDEX
    Explanations

    advice or recommendation

    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
    éĹ¯
    -0.11
    æīĭ游
    -0.10
     Nic
    -0.09
    æīįåįİ
    -0.09
    æľĢå°ij
    -0.09
    èĩ³å°ij
    -0.09
    åĴĮå¹³
    -0.09
    æĽ¾åľ¨
    -0.09
    æĪĸå¤ļæĪĸå°ij
    -0.08
    ober
    -0.08
    POSITIVE LOGITS
    è½»æĺĵ
    0.13
    æį®æѤ
    0.10
    .Arg
    0.09
    æ±Ĺ
    0.09
    bai
    0.09
    æĮĩæľĽ
    0.09
    çī¹æĦı
    0.09
    HEN
    0.09
    ä»İä¸Ń
    0.08
    以æѤ
    0.08
    Activations Density 0.042%

    No Known Activations