© 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. 13739
    Prev
    Next
    INDEX
    Explanations

    opportunity and support

    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
    amm
    -0.20
    dma
    -0.20
    PRS
    -0.19
    éĻį
    -0.19
    å¤ı
    -0.19
    ÙĪØ·
    -0.19
     Scalars
    -0.18
    鼩
    -0.18
    缩å°ı
    -0.18
    çī¯
    -0.18
    POSITIVE LOGITS
     alike
    0.22
    rien
    0.20
    çļĦå¿ĥæĥħ
    0.20
    ims
    0.19
    etus
    0.19
    èĩ¾
    0.19
    å¤Ł
    0.19
    å¿ĥæĥħ
    0.19
    æľ¬ç½ij
    0.18
     kuk
    0.18
    Activations Density 0.181%

    No Known Activations