© 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. 15902
    Prev
    Next
    INDEX
    Explanations

    sounds related to speakers and speech

    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
    ä¹IJè§Ĥ
    -0.21
    arkan
    -0.21
    å°ıå¿ĥ
    -0.21
    ulg
    -0.20
     backpage
    -0.20
    éĹªèĢĢ
    -0.20
    飧æĢ§
    -0.20
     handjob
    -0.20
    æŁĶæĢ§
    -0.20
    æİı
    -0.20
    POSITIVE LOGITS
    åIJ¬å¾Ĺ
    0.35
    éŁ³
    0.32
    å£°éŁ³
    0.31
     noise
    0.30
    çĽijåIJ¬
    0.29
    åIJ¬åĬĽ
    0.29
    åĻªéŁ³
    0.29
    åĻªå£°
    0.28
    åIJ¬ä¼Ĺ
    0.28
     listener
    0.28
    Activations Density 0.062%

    No Known Activations