© 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. 15419
    Prev
    Next
    INDEX
    Explanations

    certainty and clarity

    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
    å¹ķ
    -0.23
    ilogue
    -0.18
     Downs
    -0.18
    DataURL
    -0.18
    å¿łè¯ļ
    -0.17
    ture
    -0.17
    æīįèĥ½
    -0.17
    maries
    -0.17
    åIJİç»Ń
    -0.17
    /T
    -0.17
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.30
     anymore
    0.26
    anything
    0.20
    åĽŀäºĭ
    0.19
     anything
    0.19
    æĺĿ
    0.19
    ä»»ä½ķ人
    0.19
    太ä¹ħ
    0.18
    è¿ĻäºĽä¸ľè¥¿
    0.18
    ross
    0.18
    Activations Density 0.118%

    No Known Activations