© 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. 16360
    Prev
    Next
    INDEX
    Explanations

    recovery room

    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
     landing
    -0.21
    æĹłæķ°æ¬¡
    -0.20
    åIJĪ
    -0.20
     instant
    -0.19
    instant
    -0.19
    æ¯ıå½ĵ
    -0.19
    æĮĩ示
    -0.18
    åĽ½äºº
    -0.18
    .spatial
    -0.18
     folding
    -0.18
    POSITIVE LOGITS
    éħĴä¸ļ
    0.26
     Protect
    0.20
    ัà¸Ķ
    0.20
    éĩijèŀįå¸Ĥåľº
    0.19
    èŃ·
    0.18
    subst
    0.18
     Semiconductor
    0.18
    稳妥
    0.18
    Original
    0.18
    æĬ¤
    0.18
    Activations Density 0.002%

    No Known Activations