© 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. 1554
    Prev
    Next
    INDEX
    Explanations

    old cartridge or adhesive

    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
    rams
    -0.23
    ä¹Łåıªèĥ½
    -0.23
    æłĩæĺİ
    -0.22
    urve
    -0.22
     skl
    -0.22
    ä¸Ģä¸Ŀ
    -0.22
     playable
    -0.22
    æĥ³èµ·äºĨ
    -0.21
    -runtime
    -0.21
    æľĢ容æĺĵ
    -0.21
    POSITIVE LOGITS
    æŧ
    0.73
    èĪĬ
    0.63
     old
    0.57
    old
    0.54
    (old
    0.52
    	old
    0.51
     previous
    0.49
     Old
    0.48
     cũ
    0.46
    Old
    0.46
    Activations Density 0.200%

    No Known Activations