© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 105
    Prev
    Next
    INDEX
    Explanations

    batteries and cells

    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
     Hearth
    -0.23
     Reign
    -0.23
    layer
    -0.23
    æĪ·åı£
    -0.23
    ymm
    -0.22
     portal
    -0.22
     coron
    -0.22
     mái
    -0.22
    çļĩåĨł
    -0.22
    å¢ĻéĿ¢
    -0.22
    POSITIVE LOGITS
     batteries
    0.34
    çĶµæ±ł
    0.26
     electro
    0.26
    çĶµæºIJ
    0.26
    çİ©åħ·
    0.24
    çĶµåĬ¨
    0.24
    ammo
    0.24
     Buffered
    0.24
    åħīçĶµ
    0.23
    æĻºèĥ½æīĭæľº
    0.23
    Activations Density 0.016%

    No Known Activations