© 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. 15609
    Prev
    Next
    INDEX
    Explanations

    voice or vocal quality

    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
    饮çĶ¨
    -0.20
    weise
    -0.20
    æĭįæĭį
    -0.20
    çļĦåģļæ³ķ
    -0.20
    /extensions
    -0.20
    欤
    -0.19
    并ä¸įå¤ļ
    -0.19
    /mod
    -0.19
    家éŨåı£
    -0.19
    è¾ĥå¤ļ
    -0.19
    POSITIVE LOGITS
     intact
    0.23
    ynth
    0.22
    åłª
    0.20
    åĴĮ
    0.18
    çī¹çĤ¹
    0.18
    ä¸ĬçļĦ
    0.18
    èĩ
    0.18
    åĴĮæĬĢæľ¯
    0.17
    ISO
    0.17
     Lane
    0.17
    Activations Density 0.013%

    No Known Activations