© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15185
    Prev
    Next
    INDEX
    Explanations

    Ayn-quoting

    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
    æ¬ł
    -0.22
    èĤł
    -0.21
    illis
    -0.20
    罪
    -0.20
    éħ
    -0.19
    Ĥæķ°
    -0.19
    æķ°çłģ
    -0.19
    è°ı
    -0.19
    è½½
    -0.18
    鸣
    -0.18
    POSITIVE LOGITS
    utters
    0.22
    éĴIJ
    0.22
    çŃĿ
    0.20
    èĩ¾
    0.20
    çĿĩ
    0.20
     flaw
    0.19
    èĩªçĶ±
    0.19
    æĦŁæĥħ
    0.19
    itet
    0.19
     steel
    0.18
    Activations Density 0.014%

    No Known Activations