© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 89
    Prev
    Next
    INDEX
    Explanations

    fill in or fill out forms

    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
    æī¹åĪ¤
    -0.22
    ä¸įåı¯èĥ½
    -0.22
    archs
    -0.22
     newObj
    -0.22
    ARCH
    -0.22
    rome
    -0.22
     defaultProps
    -0.21
     quê
    -0.21
    edBy
    -0.21
    alic
    -0.21
    POSITIVE LOGITS
     below
    0.29
     email
    0.27
     Email
    0.26
    below
    0.24
    ä¸ĭéĿ¢
    0.24
    以ä¸ĭ
    0.23
    -email
    0.23
     drop
    0.23
    Email
    0.23
    onso
    0.22
    Activations Density 0.004%

    No Known Activations