© 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. 12803
    Prev
    Next
    INDEX
    Explanations

    registered trademark symbol ®

    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
    çįł
    -0.21
    /or
    -0.16
    .xml
    -0.16
    aje
    -0.16
    çĭŀ
    -0.16
    èĢ¸
    -0.15
    åĿ³
    -0.15
    оÑĢм
    -0.15
    weise
    -0.15
    shi
    -0.15
    POSITIVE LOGITS
    ï¸ı
    0.49
    ï¸
    0.22
    ãĢħ
    0.19
    sWith
    0.18
    çļĦ大
    0.18
    éĤ¸
    0.17
    åIJĮå¿ĥ
    0.17
    ATRIX
    0.17
    chw
    0.17
    åħļæĢ»æĶ¯
    0.17
    Activations Density 0.006%

    No Known Activations