© 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. 16410
    Prev
    Next
    INDEX
    Explanations

    radio and public broadcasting

    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
    rapper
    -0.21
    祧
    -0.20
     ctor
    -0.20
    ASA
    -0.19
    èĺħ
    -0.19
    æĥ¡
    -0.19
    éĸī
    -0.19
    æIJŀç¬ij
    -0.18
    chl
    -0.18
     bab
    -0.18
    POSITIVE LOGITS
    çĶµåı°
    0.23
    èµĦéĩij
    0.22
     mush
    0.20
    /pub
    0.19
     Radio
    0.19
     ÙĨÙĤ
    0.19
     radio
    0.19
     radios
    0.19
    ä¿®åħ»
    0.19
    radi
    0.19
    Activations Density 0.009%

    No Known Activations