© 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. 460
    Prev
    Next
    INDEX
    Explanations

    fuel blend/substitution

    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
    Labour
    -0.25
     mÃłn
    -0.25
     outward
    -0.24
     vak
    -0.24
     Orch
    -0.24
     bedrooms
    -0.24
    ä»ŀ
    -0.24
     privacy
    -0.24
     keyboard
    -0.24
     Keyboard
    -0.23
    POSITIVE LOGITS
    _blend
    0.40
     blends
    0.39
    æĽ¿ä»£
    0.39
    æ··åIJĪ
    0.37
    blend
    0.35
    åħ¼å®¹
    0.35
     substitution
    0.35
     mix
    0.34
     blend
    0.34
     substitute
    0.34
    Activations Density 0.019%

    No Known Activations