© 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. 2169
    Prev
    Next
    INDEX
    Explanations

    the preceded by specific terms

    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
    槽
    -0.27
     pits
    -0.26
    迷人
    -0.26
    å°ıå°ıçļĦ
    -0.25
     hardest
    -0.24
    wards
    -0.24
    åĺĺ
    -0.24
     vaz
    -0.24
     choc
    -0.23
     scratched
    -0.23
    POSITIVE LOGITS
     Framework
    0.26
     Notice
    0.26
     guidelines
    0.26
     Program
    0.26
     regulations
    0.26
     Availability
    0.26
     extrapol
    0.25
    åIJĪä½ľåįıè®®
    0.25
     Guidelines
    0.25
     Acceler
    0.25
    Activations Density 0.110%

    No Known Activations