© 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. 19737
    Prev
    Next
    INDEX
    Explanations

    Google LLC or company suffixes

    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
    leur
    -0.08
    ç»Ļä»ĸ们
    -0.08
    å¯Ł
    -0.08
    å°¾
    -0.08
    ì§ĢëĬĶ
    -0.08
    AFX
    -0.07
    ç²¾çģµ
    -0.07
    ç»Ļä½łä»¬
    -0.07
    亲çĪ±çļĦ
    -0.07
    深交
    -0.07
    POSITIVE LOGITS
    人éĢī
    0.10
    ç»į
    0.09
     окол
    0.09
    çĿĽ
    0.09
     pun
    0.09
    å¼łæī¬
    0.09
    æŀī
    0.08
    éķŀ
    0.08
    欣åĸľ
    0.08
     Worse
    0.08
    Activations Density 0.473%

    No Known Activations