© 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. 880
    Prev
    Next
    INDEX
    Explanations

    explaining how to do something

    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
    ido
    -0.23
     dipped
    -0.23
    itch
    -0.22
     spurred
    -0.21
    ighted
    -0.21
    ippers
    -0.21
    äºĨ好å¤ļ
    -0.21
    ä¿®
    -0.21
     weakest
    -0.21
    raf
    -0.21
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.33
    åħ·ä½ĵ
    0.33
     specific
    0.33
     exactly
    0.32
     specifics
    0.32
    åħ·ä½ĵåĨħ容
    0.31
    çļĦåħ·ä½ĵ
    0.31
    ä»»ä½ķä¸Ģ个
    0.31
    ä»»ä½ķ
    0.30
    æľīä»»ä½ķ
    0.30
    Activations Density 0.039%

    No Known Activations