© 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. 15176
    Prev
    Next
    INDEX
    Explanations

    parking lot or fees

    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
    IDL
    -0.20
     Airways
    -0.19
     Stark
    -0.18
    addOn
    -0.18
    heid
    -0.18
    失èIJ½
    -0.18
    addChild
    -0.18
    Ñĥж
    -0.18
    éĻĢ
    -0.18
    æ¡£
    -0.17
    POSITIVE LOGITS
    æľºä¼ļ
    0.23
    éĹ®é¢ĺæĺ¯
    0.19
    ä¸Ģä½į
    0.19
    ford
    0.19
    缮çĿ¹
    0.18
    èĩªçIJĨ
    0.18
    finder
    0.18
    æ©Łæľĥ
    0.18
    èĤĩäºĭ
    0.18
    ä¸įäºĨ
    0.18
    Activations Density 0.004%

    No Known Activations