© 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. 16423
    Prev
    Next
    INDEX
    Explanations

    Names, companies, or teams

    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
    orem
    -0.23
    ity
    -0.18
    izer
    -0.17
    ÑģÑı
    -0.16
    elta
    -0.16
    /her
    -0.16
     dolayı
    -0.15
    ail
    -0.15
    amiento
    -0.15
    edList
    -0.15
    POSITIVE LOGITS
    esco
    0.19
    Made
    0.17
    ingt
    0.17
    ãģ¾ãģ¾
    0.17
    çīĮçħ§
    0.17
    éĢļçķħ
    0.16
    çķħéĢļ
    0.15
    ä¼Ĭæĸ¯
    0.15
    夫å¦ĩ
    0.15
    uther
    0.15
    Activations Density 0.004%

    No Known Activations