© 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. 12049
    Prev
    Next
    INDEX
    Explanations

    design patterns or symbolism

    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
    AILS
    -0.21
    scp
    -0.20
    è´¿
    -0.20
    è¢ħ
    -0.19
     Lotto
    -0.19
     Garn
    -0.19
    URY
    -0.19
     \@
    -0.18
     Scr
    -0.18
    èģĨ
    -0.17
    POSITIVE LOGITS
    æĦıè¯Ĩ
    0.23
    èĩªè§ī
    0.23
    à¹Ģà¸ķ
    0.23
     formal
    0.21
     subconscious
    0.21
    åıįæĬĹ
    0.20
    æĦıè¯ĨåĪ°
    0.19
     strangers
    0.19
    ä¹Łæ²¡æľī
    0.18
    è¿Ļä¹Īå¤ļ
    0.18
    Activations Density 0.172%

    No Known Activations