© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51616
    Prev
    Next
    INDEX
    Explanations

    financial incentives and outcomes

    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
    åĪĥ
    -0.09
    çĶ¨å·¥
    -0.08
     vari
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    TA
    -0.08
    tera
    -0.08
    æ²®
    -0.08
    äºļè¿IJ
    -0.08
    çļĦæĦŁæĥħ
    -0.08
     Lester
    -0.08
    POSITIVE LOGITS
    èĤ¡ä¸ľ
    0.12
    åĿIJ
    0.10
    åĽ½æľīèµĦ产
    0.10
     пÑĢид
    0.09
    èĤ©
    0.09
    æīŃ
    0.09
    assin
    0.09
    gv
    0.09
    为广大
    0.09
    çŁ¥ä¹İ
    0.09
    Activations Density 0.024%

    No Known Activations