© 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. 16041
    Prev
    Next
    INDEX
    Explanations

    summer and its features

    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
    è¸ŀ
    -0.17
    ä»ĬçĶŁ
    -0.17
    enberg
    -0.16
    åĩºäºİ
    -0.15
    è°ģèĥ½
    -0.15
    овÑĭй
    -0.15
    sam
    -0.15
    sat
    -0.15
    edly
    -0.15
    ema
    -0.15
    POSITIVE LOGITS
    èĩ¾
    0.19
    æŶèĬĤ
    0.19
    oral
    0.19
    ous
    0.18
    деÑģÑıÑĤ
    0.18
    çĤİçĥŃ
    0.18
    uler
    0.17
    ously
    0.16
    OUS
    0.16
    isle
    0.16
    Activations Density 0.015%

    No Known Activations