© 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. 14283
    Prev
    Next
    INDEX
    Explanations

    technical discussion links

    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
    骥
    -0.20
    anke
    -0.19
    conc
    -0.19
     tgt
    -0.18
    åī¯æľ¬
    -0.18
    _tgt
    -0.18
     surplus
    -0.18
    laughter
    -0.18
    满äºĨ
    -0.17
    çĥ
    -0.17
    POSITIVE LOGITS
    è¯Ħè®®
    0.22
    æĮĩçĶ²
    0.20
    建åįİ
    0.20
    æĺ¯æľĢ好çļĦ
    0.19
    è¿Ļ个éĹ®é¢ĺ
    0.18
    uzione
    0.18
    éķŃ
    0.18
    ä¼ĺäºİ
    0.17
    eah
    0.17
    享æľī
    0.17
    Activations Density 0.002%

    No Known Activations