© 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. 22529
    Prev
    Next
    INDEX
    Explanations

    childhood obesity and unemployment

    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
    awn
    -0.09
    azi
    -0.09
    çĦļ
    -0.08
    平淡
    -0.08
    ä¸ļä½Ļ
    -0.08
    妪
    -0.08
    burgh
    -0.08
    [Math
    -0.08
    ç¦ģå¿Į
    -0.08
    åķ¬
    -0.08
    POSITIVE LOGITS
    严éĩįçļĦ
    0.12
    严峻
    0.12
     unemployment
    0.12
     rates
    0.12
    çİĩ为
    0.11
    失ä¸ļ
    0.10
    çİĩè¾¾åĪ°
    0.10
    çİĩ
    0.10
    çݰ象
    0.10
    è´«ç©·
    0.10
    Activations Density 0.349%

    No Known Activations