© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    musicians' 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
    é¥ķ
    -0.23
    èĵĸ
    -0.23
    佯
    -0.22
    porn
    -0.21
    è¹Ī
    -0.21
    porno
    -0.21
    çIJĨå·¥
    -0.20
    fds
    -0.19
    海滨
    -0.19
    avs
    -0.19
    POSITIVE LOGITS
    å¹¿æ³Ľ
    0.20
     paralle
    0.20
    ä¼´
    0.19
     Normally
    0.19
    íĴį
    0.18
    ä¸Ģæŀ¶
    0.18
    èĮĨ
    0.18
    MSG
    0.18
    çŃ·åŃIJ
    0.18
     triplet
    0.17
    Activations Density 0.014%

    No Known Activations