© 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. 13443
    Prev
    Next
    INDEX
    Explanations

    need assistance

    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
    Ĥæķ°
    -0.20
    ennen
    -0.20
    çİ®
    -0.20
    udo
    -0.20
    åķĸ
    -0.19
    ç©¿è¿ĩ
    -0.18
    åIJĥçļĦ
    -0.18
    лÑij
    -0.18
     desk
    -0.18
    åħ¬åħ±
    -0.18
    POSITIVE LOGITS
    LI
    0.19
     Aston
    0.19
    迤
    0.19
    inda
    0.18
    è³¼
    0.18
    éĢłæĪIJäºĨ
    0.18
    anst
    0.18
     Forgotten
    0.18
    è¡ĮæĶ¿åĮº
    0.17
    ë³ij
    0.17
    Activations Density 0.014%

    No Known Activations