© 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. 26600
    Prev
    Next
    INDEX
    Explanations

    recipe or formula

    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
    ÑģÑĤи
    -0.09
    bench
    -0.09
    itness
    -0.09
    éĴĵé±¼
    -0.08
    åį§
    -0.08
     à¹Ĩ
    -0.08
    ãĤ«ãĥĨ
    -0.08
    .Timeout
    -0.08
    habi
    -0.08
    ournament
    -0.08
    POSITIVE LOGITS
    recipe
    0.10
    éħįæĸ¹
    0.10
     recipe
    0.09
    leine
    0.09
    èĤĦ
    0.09
    ACTIVE
    0.09
    åħ¬å¼ı
    0.09
     zest
    0.08
    idata
    0.08
    åIJĦè¡Į
    0.08
    Activations Density 0.017%

    No Known Activations