© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13653
    Prev
    Next
    INDEX
    Explanations

    lava flow, molten slag, molten metal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ofday
    -0.20
    ularity
    -0.20
    ç¿ĺ
    -0.18
    aira
    -0.17
    Opens
    -0.17
    /history
    -0.17
    .aggregate
    -0.17
     hơi
    -0.17
     лÑİбим
    -0.16
    æĥ®
    -0.16
    POSITIVE LOGITS
     lava
    0.20
    é¹ķ
    0.19
    段
    0.19
     flow
    0.19
    nio
    0.18
    æµģ
    0.18
     segment
    0.18
     chảy
    0.18
    çĨĶ
    0.18
    à¹Ħหล
    0.18
    Activations Density 0.005%

    No Known Activations