© 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. 11629
    Prev
    Next
    INDEX
    Explanations

    time stamps and separators

    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
    alon
    -0.19
    åļĦ
    -0.18
    ç®ĸ
    -0.18
    èİ«åIJįåħ¶
    -0.18
    çĶļ
    -0.18
     midd
    -0.17
    为æѤ
    -0.17
    UNT
    -0.17
    unfold
    -0.17
    yles
    -0.17
    POSITIVE LOGITS
    óm
    0.20
     Horn
    0.19
    é¦Ļæ°Ķ
    0.19
    çĢij
    0.19
     horn
    0.18
    enerator
    0.18
    åĩ»
    0.18
    çݰ身
    0.18
    ä¸Ģéĺµ
    0.18
     yarı
    0.18
    Activations Density 0.037%

    No Known Activations