© 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. 14837
    Prev
    Next
    INDEX
    Explanations

    green retrofit

    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
    èĸªèµĦ
    -0.21
    åĮĹ京æŶéĹ´
    -0.21
    yne
    -0.20
    麻éĨī
    -0.20
    ä¸ĸçķĮç»ıæµİ
    -0.20
    TASK
    -0.20
    CRY
    -0.19
     masculine
    -0.19
    Cas
    -0.19
     Casual
    -0.19
    POSITIVE LOGITS
    åħ¥æĪ·
    0.27
    绿èī²
    0.27
    å®īè£ħ
    0.26
    绿
    0.25
    èĬĤèĥ½
    0.25
    green
    0.25
     retrofit
    0.24
    GREEN
    0.24
     green
    0.24
    .green
    0.23
    Activations Density 0.017%

    No Known Activations