© 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. 50888
    Prev
    Next
    INDEX
    Explanations

    president and prime minister

    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
    èĨĺ
    -0.10
    åĨ³èĥľ
    -0.09
    çļ±çº¹
    -0.09
    常å§Ķ
    -0.09
     Chall
    -0.09
    éķ¿çĽ¸
    -0.08
    åħ§éĥ¨
    -0.08
    CAA
    -0.08
     internal
    -0.08
    ç»ijæŀ¶
    -0.08
    POSITIVE LOGITS
    对ä»ĸ们
    0.10
    äºķ
    0.09
    uese
    0.09
    ramid
    0.09
    éħ·
    0.09
    LOUR
    0.09
    çĢĽ
    0.08
    对ä»ĸ
    0.08
    нÑĮ
    0.08
    оÑĩнÑĭÑħ
    0.08
    Activations Density 0.063%

    No Known Activations