© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2762
    Prev
    Next
    INDEX
    Explanations

    I know that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åħ¬åħĥåīį
    -0.23
    å©¿
    -0.23
    ä½ķå¤Ħ
    -0.22
    ugu
    -0.22
    æīįç®Ĺ
    -0.22
    \\\
    -0.21
    -desc
    -0.21
    åħ¥æĪ·
    -0.20
    unpack
    -0.20
    è¿ģ移
    -0.20
    POSITIVE LOGITS
    æľīäºĽ
    0.32
    ä¸įå°ij人
    0.30
    å¾Īå¤ļ人
    0.29
    æĬĢæľ¯äººåijĺ
    0.28
    æľīä¸įå°ij
    0.28
     many
    0.27
    æľīå¾Īå¤ļ
    0.27
    æľīä¸ĢäºĽ
    0.27
     technically
    0.26
    å¾Īå¤ļæľĭåıĭ
    0.26
    Activations Density 0.022%

    No Known Activations