© 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. 6457
    Prev
    Next
    INDEX
    Explanations

    welfare and social programs

    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
    åĴĮå®ĮåĸĦ
    -0.12
    å½ĵæĹ¥
    -0.10
    çĿĽ
    -0.10
    麻çĥ¦
    -0.10
    ÌĢ
    -0.10
    ILES
    -0.10
    é¹ħ
    -0.10
    åŃIJéĩĮ
    -0.09
    urre
    -0.09
    çĥ¦
    -0.09
    POSITIVE LOGITS
    ç«Ļ
    0.08
    oner
    0.08
    å°ĸ
    0.08
     Fleet
    0.08
    lush
    0.08
    hx
    0.07
    Äł
    0.07
    çIJĨ
    0.07
    lek
    0.07
    æĸ°ä¸ŃåĽ½
    0.07
    Activations Density 0.007%

    No Known Activations