© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    government bodies and organizations

    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
    æŁĿ
    -0.23
    Mutable
    -0.23
     Discussions
    -0.22
     expend
    -0.21
    Equality
    -0.20
    _workspace
    -0.20
    equality
    -0.20
    Representation
    -0.20
     Buyers
    -0.20
     shake
    -0.20
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.28
    å¼ķèµ·çļĦ
    0.27
    对åħ¶
    0.24
    æīĢå±ŀ
    0.24
    èĢĮéĿŀ
    0.24
    ahi
    0.24
    rais
    0.24
    åĪĺæµ·
    0.24
    èħ°
    0.23
    è¿ĺæĺ¯
    0.23
    Activations Density 0.474%

    No Known Activations