© 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. 513
    Prev
    Next
    INDEX
    Explanations

    explanation. (e.g. "arrangement")

    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
    éģĹçķĻ
    -0.25
    OSP
    -0.23
    FACT
    -0.22
    iez
    -0.21
    _representation
    -0.21
    Ta
    -0.21
    orse
    -0.21
    breadcrumbs
    -0.21
    FT
    -0.21
    sie
    -0.21
    POSITIVE LOGITS
    æľĪä¸Ń
    0.24
    çľĭä»ĸ
    0.24
     vegetarian
    0.23
     Monthly
    0.22
    æĴ¸
    0.22
    ç´łé£Ł
    0.22
     alphabetical
    0.22
    æ¯ı个æľĪ
    0.21
    æĥŁ
    0.21
     unlimited
    0.21
    Activations Density 0.002%

    No Known Activations