© 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. 39352
    Prev
    Next
    INDEX
    Explanations

    thinking about past regrets

    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
    å½ĵåľº
    -0.09
    åIJ¸
    -0.09
    åĬ¡
    -0.09
    gre
    -0.09
    åĿļ
    -0.09
    åIJ¸åħ¥
    -0.09
    缨
    -0.08
    çľĭä¸Ģä¸ĭ
    -0.08
    éĨį
    -0.08
    æĤħ
    -0.08
    POSITIVE LOGITS
    æĢĿ念
    0.20
    æĥ³å¿µ
    0.17
    æĥ¦
    0.14
    æĢĢ念
    0.12
    念
    0.11
    åı¯æĥ³
    0.10
    çīµæĮĤ
    0.10
    æĥ³çĿĢ
    0.09
    å¾Īæĥ³
    0.09
    æĢĿ
    0.09
    Activations Density 0.032%

    No Known Activations