© 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. 14089
    Prev
    Next
    INDEX
    Explanations

    vector field

    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
    娣
    -0.21
    çķ¿
    -0.19
    kee
    -0.19
    áĥ©
    -0.18
    ãĥ¬ãĤ¹
    -0.18
    crc
    -0.18
    ãĤĵãģ§
    -0.18
    ä¸Ĭåįĩ
    -0.18
    ellers
    -0.17
    主管éĥ¨éŨ
    -0.17
    POSITIVE LOGITS
    çŁ¢
    0.37
     vector
    0.37
     vectors
    0.37
    -vector
    0.33
     Vector
    0.33
    vector
    0.31
    Vectors
    0.30
    vec
    0.29
     vec
    0.28
    çļĦæĸ¹åIJij
    0.28
    Activations Density 0.226%

    No Known Activations