© 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. 13302
    Prev
    Next
    INDEX
    Explanations

    small business growth and support

    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
    åĢĻ
    -0.22
    çļĦè®°å¿Ĩ
    -0.21
    adm
    -0.20
    Extra
    -0.20
    ist
    -0.20
    èĤĩäºĭ
    -0.20
    å®īæ£Ģ
    -0.20
    责任人
    -0.20
    ox
    -0.19
    history
    -0.19
    POSITIVE LOGITS
    ä¸Ńå°ıä¼ģä¸ļ
    0.40
    帮åĬ©ä¼ģä¸ļ
    0.39
    å°ıå¾®ä¼ģä¸ļ
    0.33
    对ä¼ģä¸ļ
    0.32
    åĪĽä¸ļèĢħ
    0.32
    ä¼ģä¸ļ家
    0.31
    为ä¼ģä¸ļ
    0.31
    çĶŁæĦı
    0.29
     businesses
    0.29
    åĪĽä¸ļ
    0.28
    Activations Density 0.057%

    No Known Activations