© 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. 11863
    Prev
    Next
    INDEX
    Explanations

    TV show titles and names

    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
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.20
    家éķ¿ä»¬
    -0.20
     Ivanka
    -0.19
     дов
    -0.19
    æīŃ转
    -0.19
    ovi
    -0.19
    以ä¸ĬçļĦ
    -0.19
    \brief
    -0.19
    éĻį温
    -0.18
    åŃ©åŃIJçļĦ
    -0.18
    POSITIVE LOGITS
    oner
    0.19
     episode
    0.18
    .Root
    0.18
    .PageSize
    0.18
    åĬ«
    0.18
    åĢŁ
    0.17
    æ²Ł
    0.17
    nge
    0.17
    ellant
    0.17
    æ§
    0.17
    Activations Density 0.001%

    No Known Activations