© 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. 453
    Prev
    Next
    INDEX
    Explanations

    legal citations with citations

    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
    æĤ¬æµ®
    -0.22
    åĪĨéĴŁåIJİ
    -0.22
    è¿Ļä¸ĢåĪ»
    -0.22
    abaj
    -0.21
     anytime
    -0.21
     appare
    -0.21
    ¤í
    -0.21
    *sp
    -0.20
    缮åīį为æŃ¢
    -0.20
     Blizzard
    -0.20
    POSITIVE LOGITS
    墩
    0.23
     ohio
    0.23
    æįŁå®³
    0.22
     §
    0.21
     cited
    0.21
     Sellers
    0.21
    èĭ¦
    0.21
     grade
    0.21
    cit
    0.21
     заÑĢегиÑģÑĤ
    0.20
    Activations Density 0.059%

    No Known Activations