© 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. 16577
    Prev
    Next
    INDEX
    Explanations

    "home" or "properties" followed by delimiters

    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
     dim
    -0.19
    assembly
    -0.19
    xin
    -0.19
    åĭŁ
    -0.18
     wave
    -0.18
    å¼ĩ
    -0.18
    par
    -0.18
    âĢ¹
    -0.18
    [/
    -0.18
    felt
    -0.18
    POSITIVE LOGITS
    å°¸ä½ĵ
    0.23
    deen
    0.21
    ä¹ĵ
    0.20
    alach
    0.20
    å¤Ħç½®
    0.19
    åĽ½æľī
    0.19
    åĨĽäºº
    0.19
    鼶è·Ŀ离
    0.19
    [".
    0.18
    æĤĦçĦ¶
    0.18
    Activations Density 0.010%

    No Known Activations