© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14960
    Prev
    Next
    INDEX
    Explanations

    wall plaster surfaces

    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
    apur
    -0.22
    park
    -0.21
    åĮĻ
    -0.21
     Flip
    -0.20
    laws
    -0.20
    grounds
    -0.19
    åĵ²
    -0.19
     park
    -0.19
    >Last
    -0.19
    éħĭ
    -0.19
    POSITIVE LOGITS
    å¢ĻéĿ¢
    0.34
    å¢Ļä½ĵ
    0.28
    åIJĬ顶
    0.27
    çŁ³èĨı
    0.27
    楼
    0.25
    å¢Ļ
    0.24
    æĭĨéĻ¤
    0.22
    ollapse
    0.22
    å¹³æķ´
    0.22
    å¢Ļå£ģ
    0.22
    Activations Density 0.041%

    No Known Activations