© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 446
    Prev
    Next
    INDEX
    Explanations

    real estate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ype
    -0.29
    ogne
    -0.24
    tesy
    -0.23
     graffiti
    -0.23
    客人
    -0.23
     lawy
    -0.22
     cá»Ļng
    -0.21
    åŃĹæ¯į
    -0.21
    åĢĻ
    -0.21
    æīĵæī°
    -0.21
    POSITIVE LOGITS
    hift
    0.28
    çĻ¾å¹´
    0.24
    表çݰ为
    0.24
     GDP
    0.24
     equivalents
    0.24
     Goods
    0.23
     entitlement
    0.23
    ifiable
    0.23
    _RENDERER
    0.23
    å¢ŀåĬłåĢ¼
    0.23
    Activations Density 0.013%

    No Known Activations