© 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. 16515
    Prev
    Next
    INDEX
    Explanations

    radio and broadcast media

    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
     Seats
    -0.21
    容è²Į
    -0.21
    èĩ¾
    -0.20
    åĬŀäºĭ
    -0.19
     Synopsis
    -0.19
    åħĥå®Ŀ
    -0.18
    cling
    -0.18
    æ²ŁéĢļ
    -0.18
    ooth
    -0.18
    vens
    -0.18
    POSITIVE LOGITS
    ç§įåŃIJ
    0.21
    éĢį
    0.20
     appreciation
    0.20
    é²²
    0.19
    åĪģ
    0.19
    åľ°ä¸ĭ
    0.19
     seeds
    0.18
    åĻ©
    0.18
    rom
    0.18
     curator
    0.18
    Activations Density 0.027%

    No Known Activations