© 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. 27446
    Prev
    Next
    INDEX
    Explanations

    family history and surnames

    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
    æ¯ı天éĥ½
    -0.10
    rede
    -0.10
    æĺĨä»ij
    -0.09
    è··
    -0.09
    åĿļæĮģ以
    -0.09
    æ¯ı天
    -0.09
    çĭİ
    -0.09
    羸
    -0.09
     Sunrise
    -0.09
    è¼ķ
    -0.08
    POSITIVE LOGITS
    å§ĵ
    0.13
    åIJİ代
    0.10
    éĤij
    0.10
    çīĴ
    0.10
    surname
    0.10
    æµĵæµĵçļĦ
    0.10
     gene
    0.09
    åįĸ家
    0.09
     surname
    0.09
     Fir
    0.09
    Activations Density 0.107%

    No Known Activations