© 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. 52705
    Prev
    Next
    INDEX
    Explanations

    US states and districts

    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
    ниÑĨ
    -0.10
    æĭ¿æĿ¥
    -0.09
    å½¹
    -0.09
    åı¯çĸij
    -0.08
    æį¢ä¸ª
    -0.08
    osl
    -0.08
    -fw
    -0.08
    arkin
    -0.08
    erox
    -0.08
    çľģæķĻèĤ²åİħ
    -0.08
    POSITIVE LOGITS
    agate
    0.10
    åĪĨå±Ģ
    0.09
     jurisdiction
    0.09
    åŁİå¸Ĥ群
    0.09
    ä¸įè§ģ
    0.09
    çĢı
    0.08
    管è¾ĸ
    0.08
    âĪĭ
    0.08
    åŁİå¸ĤçļĦ
    0.08
    èµĽåĮº
    0.08
    Activations Density 0.563%

    No Known Activations