© 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. 16019
    Prev
    Next
    INDEX
    Explanations

    IBM corporation and related entities

    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
    erno
    -0.16
    chs
    -0.16
     dÃłng
    -0.16
    讧
    -0.16
     rag
    -0.16
     cher
    -0.16
    dur
    -0.15
    faf
    -0.15
    iol
    -0.15
    anas
    -0.15
    POSITIVE LOGITS
    shire
    0.20
     corporation
    0.17
    佬
    0.17
    æ·Ģ
    0.17
    åĽ«
    0.16
    IBM
    0.16
     Corporation
    0.16
    ÙĬÙĪÙĨ
    0.16
    è¿ĻæŶ
    0.16
    _buff
    0.16
    Activations Density 0.007%

    No Known Activations