© 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. 12671
    Prev
    Next
    INDEX
    Explanations

    strup C++

    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
    à¸ĺรรม
    -0.20
    å´¦
    -0.18
    whelming
    -0.18
    ChangeListener
    -0.18
    çľĩ
    -0.18
    åŁ
    -0.18
    Md
    -0.18
    ÑģеÑĢ
    -0.17
     repro
    -0.17
    geh
    -0.17
    POSITIVE LOGITS
    æĬľ
    0.19
    çĪ±å°Ķåħ°
    0.18
     defects
    0.18
    被çĽĹ
    0.18
    顺
    0.18
    æĮĤçĿĢ
    0.17
    åīįæīĢæľªæľī
    0.17
    inator
    0.17
    tics
    0.17
    uisine
    0.17
    Activations Density 0.003%

    No Known Activations