© 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. 55204
    Prev
    Next
    INDEX
    Explanations

    craft beer and craftsmanship

    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
    æĪĸå¤ļ
    -0.11
    odian
    -0.09
    ikon
    -0.09
    worth
    -0.09
    idot
    -0.09
    çĦ±
    -0.09
    ãģĬãģĭ
    -0.08
    afone
    -0.08
    acer
    -0.08
    .dot
    -0.08
    POSITIVE LOGITS
    们éĥ½
    0.11
    ous
    0.09
    们
    0.09
    èī¯å¿ĥ
    0.09
    educt
    0.09
    omer
    0.09
    æĭĪ
    0.09
    yı
    0.09
    pest
    0.09
    èĻ±
    0.08
    Activations Density 0.003%

    No Known Activations