© 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. 15401
    Prev
    Next
    INDEX
    Explanations

    offer from, offered a, freshman, highly-rated

    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¡ĵ
    -0.18
    ç»ĵç®Ĺ
    -0.18
    åĩºè·¯
    -0.18
     наб
    -0.18
    æľĭåıĭ们
    -0.18
    _ATTACHMENT
    -0.18
    å¨Ħ
    -0.18
    uggle
    -0.17
    haus
    -0.17
     Wien
    -0.17
    POSITIVE LOGITS
    ä¼°åĢ¼
    0.23
    åħ¥åѦ
    0.21
    人æīįåŁ¹åħ»
    0.20
    çŃī级
    0.20
    è¿Ľåľº
    0.19
     kém
    0.19
    人æīį
    0.19
    åħ¥åľº
    0.19
    idel
    0.18
    è¿ĽæĿ¥
    0.18
    Activations Density 0.001%

    No Known Activations