© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    qualities of texture and consistency

    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
    ä¸ĢæĬ¹
    -0.21
    ploy
    -0.20
    æ´Ĺ澡
    -0.20
    ç½Ĥ
    -0.19
    è¦Ĩ
    -0.19
    çķĮçļĦ
    -0.19
    æ´ĹèĦ¸
    -0.19
    åĮį
    -0.19
    èĥ¡åŃIJ
    -0.19
    æĪĸå°Ĩ
    -0.19
    POSITIVE LOGITS
     qualities
    0.23
    æŁĶ软
    0.23
    æŁĶ
    0.21
    soft
    0.21
     má»ģm
    0.20
    ness
    0.19
    NESS
    0.19
    人å¿ĥ
    0.18
    éĩijåŃĹ
    0.18
     smooth
    0.18
    Activations Density 0.010%

    No Known Activations