© 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. 13729
    Prev
    Next
    INDEX
    Explanations

    Mississippi

    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
    æı¶
    -0.21
    ä¸įä¸Ģå®ļ
    -0.20
    ä¼ī
    -0.20
     donor
    -0.19
    vere
    -0.19
    æĭ¬
    -0.19
    饬
    -0.18
    ä¸įå¾Ĺè¶ħè¿ĩ
    -0.18
    åIJĪéĩij
    -0.18
    å°¬
    -0.18
    POSITIVE LOGITS
    _REPEAT
    0.22
    NL
    0.21
    nl
    0.20
     nl
    0.20
     panor
    0.19
    .nl
    0.19
    åIJĦ个çݯèĬĤ
    0.19
    æºIJæºIJ
    0.18
    -CN
    0.18
    伸æīĭ
    0.18
    Activations Density 0.008%

    No Known Activations