© 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. 591
    Prev
    Next
    INDEX
    Explanations

    want something similar

    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
     ÑĢанее
    -0.27
    inned
    -0.26
    iment
    -0.21
    elig
    -0.21
    åįĪåIJİ
    -0.21
    hone
    -0.21
    å¾Īæľī
    -0.21
    criptor
    -0.21
     problematic
    -0.21
    PERT
    -0.20
    POSITIVE LOGITS
     clarification
    0.36
    lessly
    0.33
     assistance
    0.29
     confirmation
    0.28
    çļĦä¸ĢåĪĩ
    0.27
    confirmation
    0.27
    é¢Ŀå¤ĸ
    0.25
     desperately
    0.25
    æĽ´å¤ļçļĦ
    0.25
     assurances
    0.24
    Activations Density 0.101%

    No Known Activations