© 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. 33872
    Prev
    Next
    INDEX
    Explanations

    inherit property or wealth

    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
    çķ¦
    -0.09
    èĭĹ
    -0.09
    深交
    -0.09
    宵
    -0.09
    å¼Ń
    -0.09
    åħ¬åħ³
    -0.09
    æĤłæĤł
    -0.09
     prag
    -0.09
    å®ıè§Ĥç»ıæµİ
    -0.08
    èľĵ
    -0.08
    POSITIVE LOGITS
    继æī¿
    0.19
     inheritance
    0.19
    财产
    0.17
    éģĹ产
    0.17
    inherit
    0.15
     inherit
    0.14
    heritance
    0.13
     inher
    0.12
     inherits
    0.12
    åĪĨåī²
    0.12
    Activations Density 0.119%

    No Known Activations