© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15226
    Prev
    Next
    INDEX
    Explanations

    meta wiki links and discussions

    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
    åİĨåı²æĢ§
    -0.19
    çĸıéĢļ
    -0.18
     cone
    -0.18
    ç»Ĩèħ»
    -0.18
     tract
    -0.18
     shells
    -0.17
    Dims
    -0.17
    quil
    -0.17
     industries
    -0.17
     Maz
    -0.17
    POSITIVE LOGITS
     заÑĢегиÑģÑĤ
    0.20
     пÑĢиÑıÑĤн
    0.20
    airo
    0.20
     ÐIJлекÑģан
    0.20
    uen
    0.19
     кнопк
    0.19
    ãĤ·ãĥ§
    0.19
    faker
    0.19
     ÑĢÑĥков
    0.19
    åİŁä»¶
    0.18
    Activations Density 0.019%

    No Known Activations