© 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. 15450
    Prev
    Next
    INDEX
    Explanations

    plants and flora

    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
    ogenerated
    -0.23
    âĬĭ
    -0.23
    âīĤ
    -0.23
    鱿
    -0.23
    âĩī
    -0.22
    Å°
    -0.22
    鲤
    -0.21
    鲸
    -0.21
    çįŃ
    -0.20
    à°³
    -0.20
    POSITIVE LOGITS
    常è§ģ
    0.30
    æł½åŁ¹
    0.27
    ç¹ģæ®ĸ
    0.27
    èĮİ
    0.26
    åĽŃæŀĹ
    0.26
    è¯ĨåĪ«
    0.25
    åĵģç§į
    0.25
    åIJį称
    0.25
    DESCRIPTION
    0.25
    è§Ĥèµı
    0.24
    Activations Density 0.229%

    No Known Activations