© 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. 1682
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    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
     dap
    -0.24
    ëĮĢë¡ľ
    -0.23
     Robin
    -0.22
    ëĮĢ
    -0.22
    OLS
    -0.21
    _PANEL
    -0.21
    严峻
    -0.21
     roast
    -0.21
    ropa
    -0.20
    ANS
    -0.20
    POSITIVE LOGITS
    èĭ±çī¹
    0.24
    æĺ¯ä»Ģä¹Īåij¢
    0.22
     Advent
    0.22
    otr
    0.22
    ONO
    0.21
     subt
    0.21
    aten
    0.21
     subdiv
    0.20
    客家
    0.20
    _##
    0.20
    Activations Density 0.544%

    No Known Activations