© 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. 12904
    Prev
    Next
    INDEX
    Explanations

    evoked potentials

    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
    åĪijäºĭ责任
    -0.21
    æĹħ游å±Ģ
    -0.19
    åı¯ä»¥æĬĬ
    -0.19
    è§Ħ
    -0.18
    .nc
    -0.18
    /posts
    -0.18
    åĬ³åĬ¨
    -0.18
    æ³Ľ
    -0.18
    /accounts
    -0.17
     MUT
    -0.17
    POSITIVE LOGITS
    åIJĪçIJĨçļĦ
    0.23
    OUR
    0.21
    opping
    0.19
    åIJĪçIJĨ
    0.19
     Mane
    0.18
    .setTimeout
    0.18
    ç»ŀ
    0.18
    é²IJ
    0.18
    aaS
    0.18
    èŁij
    0.17
    Activations Density 0.239%

    No Known Activations