© 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. 39937
    Prev
    Next
    INDEX
    Explanations

    bio-, -ology, -netics, -metry

    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
    çħ³
    -0.09
    etter
    -0.09
    èįª
    -0.09
    IVING
    -0.08
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    çĶ¨å¾®ä¿¡
    -0.08
    æ²Ļé¾Ļ
    -0.08
    Bean
    -0.08
    éĴ¤
    -0.08
    hire
    -0.08
    POSITIVE LOGITS
    ager
    0.10
    æŃ£åĢ¼
    0.08
    iability
    0.08
    çĥŁçģ«
    0.08
    颦
    0.08
    iplinary
    0.08
    éļĻ
    0.08
    ç²¼
    0.08
    infeld
    0.08
    imately
    0.08
    Activations Density 0.762%

    No Known Activations