© 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. 15668
    Prev
    Next
    INDEX
    Explanations

    procrastinate or fixing

    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
    sky
    -0.21
    åij½
    -0.20
    utos
    -0.20
    ï¸
    -0.20
    ryn
    -0.20
    æİ°
    -0.20
     Geb
    -0.20
    èĤ´
    -0.19
    æĢ§åij½
    -0.19
    alley
    -0.19
    POSITIVE LOGITS
    çĨ¨
    0.25
    çĸł
    0.22
    ç½®æį¢
    0.20
    occo
    0.20
     lint
    0.19
    绨
    0.19
     ÐľÐ°
    0.19
    è¡£æľį
    0.19
     procrast
    0.19
    .Marshal
    0.18
    Activations Density 0.002%

    No Known Activations