© 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. 497
    Prev
    Next
    INDEX
    Explanations

    crafting and trading items

    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
    以人为
    -0.25
     ÑĦÑĥÑĤбол
    -0.25
    èİħ
    -0.25
     Benton
    -0.25
    æ²ī浸
    -0.25
    å®īåħ¨æĦŁ
    -0.24
    åİĭè¿«
    -0.24
    å¿ł
    -0.24
    arrant
    -0.24
     walkers
    -0.24
    POSITIVE LOGITS
     rarity
    0.32
    æīĢéľĢ
    0.32
    åĿ©
    0.31
    è´§æºIJ
    0.30
    çĶŁäº§çļĦ
    0.29
    ä»·æł¼
    0.29
     recipes
    0.29
    ç¨Ģ缺
    0.28
    éħįæĸ¹
    0.28
     XOR
    0.28
    Activations Density 0.040%

    No Known Activations