© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2859
    Prev
    Next
    INDEX
    Explanations

    demystify, dewatering, decortication

    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
    éĿ¢ä¸Ĭ
    -0.24
    è¾¹ä¸Ĭ
    -0.24
    Gr
    -0.24
    ä¸ĬçļĦ
    -0.23
    etch
    -0.23
    REE
    -0.22
    rien
    -0.21
    ä¸Ĭæľī
    -0.20
    Utilities
    -0.20
     Recipes
    -0.20
    POSITIVE LOGITS
    åIJİçļĦ
    0.27
    /mit
    0.25
    åĴĮåıijå±ķ
    0.23
    åĴĮå®ĮåĸĦ
    0.22
    /remove
    0.22
    zent
    0.22
    andro
    0.22
    isto
    0.22
    enment
    0.21
    ido
    0.21
    Activations Density 0.115%

    No Known Activations