© 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. 13030
    Prev
    Next
    INDEX
    Explanations

    songs and dances

    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
    Marvel
    -0.24
    å°ĸåı«
    -0.20
    _MAXIMUM
    -0.19
    ä¸ĢåIJ¬
    -0.19
     Marvel
    -0.19
    ê°Ī
    -0.18
    åĶ¬
    -0.18
    rait
    -0.18
    ToRemove
    -0.18
    æѸ
    -0.18
    POSITIVE LOGITS
     parody
    0.25
    endar
    0.22
    åĪº
    0.20
    顶级
    0.20
     Rum
    0.20
    ä¸įåĪ°
    0.19
    èĭ«
    0.19
    对çħ§
    0.19
    ä¸į足以
    0.19
    庶
    0.18
    Activations Density 0.001%

    No Known Activations