© 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. 4361
    Prev
    Next
    INDEX
    Explanations

    repeats itself or again

    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
    quire
    -0.11
    ä¸Ģåı°
    -0.10
    äºı
    -0.10
    IBC
    -0.09
    æģ£
    -0.09
    ä¸ĢæĬĬ
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    metics
    -0.08
     bÄĥng
    -0.08
    å½»
    -0.08
    POSITIVE LOGITS
    æĪijæĺ¯
    0.09
    é¢Ľ
    0.09
    说èĩªå·±
    0.08
    cis
    0.08
    pecies
    0.08
    æĪijä¸įæĺ¯
    0.08
     previous
    0.08
     Rue
    0.08
    bris
    0.08
    以å¾Ģ
    0.08
    Activations Density 0.001%

    No Known Activations