© 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. 10842
    Prev
    Next
    INDEX
    Explanations

    Slip Op

    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
    èĢģ头
    -0.19
    tres
    -0.19
    éļIJå½¢
    -0.18
    ience
    -0.17
    lient
    -0.17
    ÑģÑģ
    -0.17
    èļ¯
    -0.17
    andid
    -0.17
    essa
    -0.17
     looping
    -0.17
    POSITIVE LOGITS
    èĢį
    0.20
     Quantity
    0.20
    าà¸ĩ
    0.19
    æ¹
    0.19
     Confirmation
    0.19
     REQUIRED
    0.18
    structors
    0.18
     عÙĦÙĬÙĩ
    0.18
     quantities
    0.18
    Quantity
    0.18
    Activations Density 0.003%

    No Known Activations