© 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. 373
    Prev
    Next
    INDEX
    Explanations

    names or titles followed by a noun

    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
    ioctl
    -0.23
    ä¸įèĪį
    -0.22
    pdo
    -0.22
     Locke
    -0.22
    pet
    -0.22
     Iron
    -0.21
    surface
    -0.21
     iron
    -0.21
     labour
    -0.21
     nargs
    -0.21
    POSITIVE LOGITS
    -inspired
    0.26
    ymes
    0.25
    енд
    0.24
     rhyme
    0.23
     sentences
    0.23
    èĪ¬çļĦ
    0.23
    -approved
    0.23
    ective
    0.23
    -ahead
    0.22
     words
    0.22
    Activations Density 0.001%

    No Known Activations