© 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. 700
    Prev
    Next
    INDEX
    Explanations

    tropical rainforests

    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
    æĵĢ
    -0.28
    éķ¦
    -0.27
    å°ı麦
    -0.27
    éĶ»
    -0.27
    å¸ĸ
    -0.26
     Salt
    -0.26
    ifax
    -0.25
     Greeks
    -0.25
    ç¾Ķ
    -0.24
    çĽIJ
    -0.24
    POSITIVE LOGITS
     jungle
    0.54
     tropical
    0.52
    forest
    0.51
     forest
    0.51
     forests
    0.50
    çĥŃ带
    0.49
     jung
    0.45
    举åįĹäºļ
    0.44
    森æŀĹ
    0.44
     Tropical
    0.44
    Activations Density 0.164%

    No Known Activations