© 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. 23325
    Prev
    Next
    INDEX
    Explanations

    biblical names and books

    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
     #:
    -0.08
    å¼ŁåŃIJ
    -0.08
    ocos
    -0.08
    å¡ij
    -0.08
    ä¸»å¼ł
    -0.08
    被éªĹ
    -0.08
    æĸ°åħ´
    -0.08
    èIJ½ä¸ĭ
    -0.07
    Tro
    -0.07
     cann
    -0.07
    POSITIVE LOGITS
    ç¾İçļĦ
    0.09
     kì
    0.09
    æĪĽ
    0.09
    ä½łè¯´
    0.09
    大åį«
    0.09
    论
    0.09
    çķ¿
    0.08
    以èī²åĪĹ
    0.08
    缴éĢļ车
    0.08
    好象
    0.08
    Activations Density 0.063%

    No Known Activations