© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    sea level floody erosion

    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
     drought
    -0.21
    åĹĵåŃIJ
    -0.20
     Kindle
    -0.20
    æīįç®Ĺ
    -0.20
    溪
    -0.19
    æĭĹ
    -0.19
     Profession
    -0.19
    æĮ¯å¥ĭ
    -0.19
    å¹²çĩ¥
    -0.19
    é£İæł¼
    -0.18
    POSITIVE LOGITS
    å¨ģèĥģ
    0.24
    ä¾µèļĢ
    0.23
    åīįéĢĶ
    0.20
    íķij
    0.20
    æľ¬æĿ¥å°±
    0.19
    EPROM
    0.19
    çºłéĶĻ
    0.19
    åīįæĻ¯
    0.19
    .pose
    0.19
    scp
    0.18
    Activations Density 0.010%

    No Known Activations