© 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. 15294
    Prev
    Next
    INDEX
    Explanations

    telephone switching communications equipment

    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
    science
    -0.22
    /tool
    -0.21
    azine
    -0.21
    殿
    -0.20
    Instagram
    -0.20
     kho
    -0.20
    _hashes
    -0.20
    æ¸ħçIJĨ
    -0.20
     Arch
    -0.19
    arch
    -0.19
    POSITIVE LOGITS
     голоÑģ
    0.28
    åij¼åı«
    0.28
    éĢļè¯Ŀ
    0.27
     erotik
    0.26
    æľįåĬ¡è´¨éĩı
    0.25
     erotisk
    0.25
    åĶ¿
    0.25
    æŃĮ声
    0.25
     Telephone
    0.24
    å½ķéŁ³
    0.24
    Activations Density 0.066%

    No Known Activations