© 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. 14090
    Prev
    Next
    INDEX
    Explanations

    musical groups and performances

    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
    æĪķ
    -0.21
    åıįå¤į
    -0.21
    åĨ·éĿĻ
    -0.21
     ÑģÑĥ
    -0.20
    磼
    -0.20
    ä»»æĢ§
    -0.20
    Ñĥй
    -0.19
    èĵij
    -0.18
    æĸĻçIJĨ
    -0.18
    åijĬè¯ī
    -0.18
    POSITIVE LOGITS
    åIJĪåĶ±
    0.29
    åħ¨ä½ĵ
    0.25
    æ¼ĶåĶ±
    0.24
    éĥ¨ä¸»ä»»
    0.22
    人æķ°
    0.22
    ä½ľåĵģ
    0.22
    å¿ĹæĦ¿èĢħ
    0.21
     performances
    0.21
    乡æĿij
    0.20
    æ¼Ķå¥ı
    0.20
    Activations Density 0.015%

    No Known Activations