© 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. 13009
    Prev
    Next
    INDEX
    Explanations

    cumulative accumulation

    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
    ened
    -0.30
    ening
    -0.27
    liness
    -0.24
    anners
    -0.16
    ivas
    -0.16
    åĪĨæµģ
    -0.16
    اÙħÙĦ
    -0.16
    fully
    -0.15
    erable
    -0.15
    anos
    -0.15
    POSITIVE LOGITS
    äºĨå¾Īå¤ļ
    0.20
    iliar
    0.20
    ä¸įäºĨ
    0.18
    bersome
    0.17
     trữ
    0.17
    ired
    0.17
    ä½Ĩä¸įéĻIJäºİ
    0.17
    lass
    0.16
    loth
    0.16
    nda
    0.16
    Activations Density 0.018%

    No Known Activations