© 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. 33869
    Prev
    Next
    INDEX
    Explanations

    organizations and publications

    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
    inte
    -0.09
    屬æĸ¼
    -0.09
    åīĸ
    -0.09
    é©°
    -0.08
    竽
    -0.08
    ipes
    -0.08
    ocol
    -0.08
     Abyss
    -0.08
    èIJ½åı¶
    -0.08
     cape
    -0.08
    POSITIVE LOGITS
    æĤį
    0.10
    uck
    0.09
     ju
    0.09
    arness
    0.09
    razier
    0.08
    onomic
    0.08
    /stretch
    0.08
    ÑĭÑĤа
    0.08
    éĢļåħ³
    0.08
    ستاÙĨ
    0.08
    Activations Density 0.001%

    No Known Activations