© 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. 12054
    Prev
    Next
    INDEX
    Explanations

    place names followed by specific affiliations

    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
     Cork
    -0.21
    uri
    -0.20
    ONUS
    -0.20
    ãģ«ä¹Ĺ
    -0.20
    ùng
    -0.19
    usa
    -0.19
     vin
    -0.18
    ãģ¤ãĤĤãĤĬ
    -0.18
     Bermuda
    -0.18
    èĢĢ
    -0.18
    POSITIVE LOGITS
    士
    0.20
    asser
    0.19
    /rs
    0.19
    社ä¼ļ主ä¹ī
    0.18
    壳
    0.18
     taxp
    0.18
    åı¤äºº
    0.18
    eldo
    0.18
    esan
    0.18
    éĴµ
    0.18
    Activations Density 0.002%

    No Known Activations