© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    effort, event, ess

    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
    çĽ¸å·®
    -0.25
    缩水
    -0.24
    è¯ĬæĸŃ
    -0.24
     Tro
    -0.23
     мÑıг
    -0.23
     reporting
    -0.23
    åªĴä½ĵæĬ¥éģĵ
    -0.23
    igrated
    -0.22
    Äħż
    -0.22
    åħīçݯ
    -0.21
    POSITIVE LOGITS
     decisive
    0.26
    大家ä¸Ģèµ·
    0.25
     exhaustion
    0.24
     lat
    0.24
     oportun
    0.24
     ultimate
    0.24
    ä¸Ģæ³¢
    0.24
     groups
    0.24
    grupo
    0.24
     crowd
    0.24
    Activations Density 0.005%

    No Known Activations