© 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. 9719
    Prev
    Next
    INDEX
    Explanations

    organizer or organisation

    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
    alach
    -0.11
    ä¸Ģ度
    -0.09
    èĥª
    -0.09
    /problems
    -0.08
    itt
    -0.08
    urrent
    -0.08
    管家
    -0.08
    év
    -0.08
    scape
    -0.08
    enas
    -0.08
    POSITIVE LOGITS
    çĿ¬
    0.15
    äºĨä¸Ģåľº
    0.13
    æİĸ
    0.11
    èµ·æĿ¥
    0.10
     меÑĢопÑĢи
    0.10
    견
    0.09
    è¿Ļåľº
    0.09
    áŀ¡
    0.09
    åĮºåŁŁåĨħ
    0.09
    ×£
    0.09
    Activations Density 0.028%

    No Known Activations