© 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. 57836
    Prev
    Next
    INDEX
    Explanations

    fertilization and cell development

    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
    å°»
    -0.10
    襻
    -0.09
    çĵ¢
    -0.09
    æıĸ
    -0.09
    кÑĤ
    -0.09
    å¼ĢåıijåĮº
    -0.09
    æĽ´è¦ģ
    -0.09
    è¦ģçĶ¨
    -0.08
    æĸ°æ¬¾
    -0.08
     Fancy
    -0.08
    POSITIVE LOGITS
    顶
    0.10
    çıŃ
    0.09
    ä¸Ģçīĩ
    0.09
    ombs
    0.09
    eker
    0.09
    -enter
    0.09
    IRON
    0.08
    ãģ»
    0.08
    ijke
    0.08
    æĸ¹åIJij
    0.08
    Activations Density 0.310%

    No Known Activations