© 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. 31370
    Prev
    Next
    INDEX
    Explanations

    goods and services

    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
    éĺ´
    -0.11
    åIJĦ个çݯèĬĤ
    -0.10
    åĪ³
    -0.09
    odal
    -0.09
    åĪ¨
    -0.09
    ana
    -0.09
     оказÑĭва
    -0.09
    ilation
    -0.08
    éĻ°
    -0.08
    èķĥ
    -0.08
    POSITIVE LOGITS
     goods
    0.12
    ivities
    0.09
    åĵģç±»
    0.09
    æĩĶ
    0.09
    åĵģ
    0.09
     åķĨåĵģ
    0.09
    åĴĮæľįåĬ¡
    0.09
    å¼ĢéŨ
    0.09
    å¯Ĵ
    0.09
    _MATERIAL
    0.09
    Activations Density 0.048%

    No Known Activations