© 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. 12122
    Prev
    Next
    INDEX
    Explanations

    drilling directional vibration amplification

    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
    ä¹Łä¸įæĺ¯
    -0.19
    CID
    -0.18
    eway
    -0.18
    ä¸įçĽ¸ä¿¡
    -0.18
    chio
    -0.18
    Interfaces
    -0.18
    anko
    -0.17
    æŃ£ä¹ī
    -0.17
    aben
    -0.17
    éĿ¢åŃĶ
    -0.17
    POSITIVE LOGITS
    æĬĢæľ¯åĴĮ
    0.28
    æĬĢæľ¯
    0.28
     technology
    0.28
     technique
    0.27
    æĬĢæľ¯çłĶåıij
    0.27
    è¿Ļç§įæĸ¹æ³ķ
    0.25
    åħĪè¿ĽæĬĢæľ¯
    0.24
    çĩİ
    0.24
    æĬĢè¡ĵ
    0.22
    è¿Ļç§įæĸ¹å¼ı
    0.22
    Activations Density 0.245%

    No Known Activations