© 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. 16080
    Prev
    Next
    INDEX
    Explanations

    accident crash wreck

    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
    pora
    -0.19
    desktop
    -0.18
    .charCodeAt
    -0.17
    ieties
    -0.17
    éĢļãĤĬ
    -0.17
    çļĦå¢ŀéķ¿
    -0.17
    ãħĹ
    -0.17
    çļĦä»»åĬ¡
    -0.17
    ovement
    -0.17
    otyping
    -0.17
    POSITIVE LOGITS
    Occurred
    0.25
    ëĭ´
    0.22
    æł¡åıĭ
    0.21
     aftermath
    0.21
    çŀij
    0.20
    å¤ļä½į
    0.20
    _OCCURRED
    0.20
    è¿ŀè¿ŀ
    0.20
    ison
    0.19
    åľºæĻ¯
    0.18
    Activations Density 0.012%

    No Known Activations