© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    Henry, Kaepernick, Rudolph, Yahoo

    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
    éļIJ身
    -0.20
    è¾Ķ
    -0.19
    loff
    -0.18
    ä¾£
    -0.18
    ç¾¹
    -0.18
    çĶµä»·
    -0.18
    åŁİåĮº
    -0.18
    éĶ£
    -0.18
    mate
    -0.18
    /inc
    -0.18
    POSITIVE LOGITS
    _decay
    0.21
    apo
    0.20
    ordo
    0.19
    å¾ģ
    0.19
    rike
    0.19
    Capacity
    0.18
    æĸľ
    0.18
    åĪ
    0.18
    ismet
    0.18
    trag
    0.18
    Activations Density 0.001%

    No Known Activations