© 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. 12177
    Prev
    Next
    INDEX
    Explanations

    sound of

    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¢Ŀ头
    -0.20
    é»Ŀ
    -0.20
    çļĦ缮åħī
    -0.19
    çĬŁ
    -0.19
     Hunger
    -0.19
    纡
    -0.18
    wizard
    -0.18
    ä½İä»·
    -0.18
    éħĭ
    -0.18
     Rider
    -0.18
    POSITIVE LOGITS
    声
    0.21
    声åĵį
    0.21
    ses
    0.21
    åĬ¾
    0.21
    cape
    0.20
     hollow
    0.20
    tracked
    0.20
     sound
    0.20
    (sound
    0.20
    éļĶçĿĢ
    0.19
    Activations Density 0.035%

    No Known Activations