© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    birthdays and godmothers

    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
    缤
    -0.09
    ä½İ温
    -0.09
    èĬĬ
    -0.09
    åIJ
    -0.09
    çŃ²
    -0.09
    éĴĵé±¼
    -0.09
    /arch
    -0.08
    åĨħè¡£
    -0.08
    éļĶçĿĢ
    -0.08
    é¹ŀ
    -0.08
    POSITIVE LOGITS
    åģĩ
    0.11
     birthdays
    0.09
    fund
    0.08
    umont
    0.08
    çĪ¶æ¯į
    0.08
    è§ģè¯ģ
    0.08
    å·§åIJĪ
    0.08
     birthday
    0.08
    bearer
    0.08
     Indust
    0.08
    Activations Density 0.110%

    No Known Activations