© 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. 49447
    Prev
    Next
    INDEX
    Explanations

    it to

    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
    çļĦ身影
    -0.10
    æľīæĿĥ
    -0.09
    alive
    -0.09
    大çĪ·
    -0.09
    shed
    -0.08
    æīĭä¸Ń
    -0.08
     аналог
    -0.08
    éķĩåħļå§Ķ
    -0.08
    çIJ¢ç£¨
    -0.08
    ç¾ļ
    -0.08
    POSITIVE LOGITS
    ugu
    0.09
    åıijçĶŁçļĦ
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    ØŃض
    0.09
     happen
    0.09
    移交
    0.09
    iginal
    0.09
    好åĥıæĺ¯
    0.08
    ighth
    0.08
     happened
    0.08
    Activations Density 0.186%

    No Known Activations