© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21760
    Prev
    Next
    INDEX
    Explanations

    tumor types

    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
    çľģéĴ±
    -0.10
    é³ĥ
    -0.10
    vais
    -0.10
    æ¦Ĥ
    -0.09
    æĴĻ
    -0.09
    æ¶
    -0.09
    ãĤ·ãĥ§ãĥĥãĥĹ
    -0.09
    ç²®
    -0.09
    èµIJ
    -0.09
     giú
    -0.09
    POSITIVE LOGITS
    é²ľ
    0.09
    主ä¸ļ
    0.08
    ÑĢо
    0.08
    ç³»
    0.08
    or
    0.08
    CO
    0.08
     fallback
    0.07
     cle
    0.07
    å¸Ń
    0.07
    æĮİ
    0.07
    Activations Density 0.482%

    No Known Activations