© 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. 35314
    Prev
    Next
    INDEX
    Explanations

    material possessions

    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
    åºļ
    -0.11
    æIJĢ
    -0.10
    odge
    -0.09
    èĻİ
    -0.09
    ì¦Ī
    -0.09
    ä¸į对
    -0.08
    临
    -0.08
    yor
    -0.08
    jur
    -0.08
    æĿĤ
    -0.08
    POSITIVE LOGITS
    çī©è´¨
    0.16
     possessions
    0.13
     material
    0.13
    çī©åĵģ
    0.13
    material
    0.12
    çī©èµĦ
    0.11
    (material
    0.11
    .material
    0.10
    -material
    0.10
    è´¢çī©
    0.10
    Activations Density 0.120%

    No Known Activations