© 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. 2486
    Prev
    Next
    INDEX
    Explanations

    arch or architecture

    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
    hood
    -0.09
    å¦ŀ
    -0.09
    ÑĢÑĥж
    -0.09
    æѤåĪ»
    -0.09
    æĢħ
    -0.08
    ennen
    -0.08
    ted
    -0.08
    anford
    -0.08
    ç¥ļ
    -0.08
    atorium
    -0.08
    POSITIVE LOGITS
    itect
    0.14
    itecture
    0.13
    aic
    0.12
    аÑħ
    0.10
    uary
    0.10
     Plenty
    0.10
    (es
    0.10
    andise
    0.10
    ÙĨÙĪ
    0.10
    ãĤħ
    0.10
    Activations Density 0.015%

    No Known Activations