© 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. 16717
    Prev
    Next
    INDEX
    Explanations

    permitted and allowed

    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¦ĨçĽĸçİĩ
    -0.20
     обÑıзаÑĤелÑĮ
    -0.20
    ê°IJ
    -0.19
    è¾ķ
    -0.18
    轿
    -0.18
     gere
    -0.18
    æħ£
    -0.18
     занÑıÑĤ
    -0.18
     деле
    -0.17
    /avatar
    -0.17
    POSITIVE LOGITS
    åħģ许
    0.31
    èĩªçĶ±
    0.28
     unlimited
    0.27
     Allowed
    0.27
     allowed
    0.26
    åħģ
    0.25
    éļıæĦı
    0.24
    Allowed
    0.24
    .allowed
    0.24
    æľīéĻIJ
    0.23
    Activations Density 0.181%

    No Known Activations