© 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. 11996
    Prev
    Next
    INDEX
    Explanations

    go to [destination]

    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
    esp
    -0.18
    ей
    -0.17
    neath
    -0.17
    ãģĦãģĨ
    -0.17
    ly
    -0.17
    ington
    -0.16
    unsch
    -0.16
     cov
    -0.16
    izons
    -0.16
    赶ä¸Ĭ
    -0.16
    POSITIVE LOGITS
     pains
    0.20
    æīĵä»Ĺ
    0.19
    å¾Ĺ太
    0.19
    人ãģ«
    0.19
     extremes
    0.18
    ä¸Ģè¶Ł
    0.18
    errupted
    0.17
    ราà¸Ĭà¸ģาร
    0.17
    otle
    0.17
    jähr
    0.16
    Activations Density 0.025%

    No Known Activations