© 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. 11989
    Prev
    Next
    INDEX
    Explanations

    followed by verb or name

    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
    scan
    -0.20
    insula
    -0.20
    alar
    -0.19
    æĽ·
    -0.19
    åİĨ
    -0.19
    åĴĿ
    -0.19
    æĥ¹
    -0.19
    æĮ£
    -0.18
    aders
    -0.18
    .qu
    -0.18
    POSITIVE LOGITS
    é»ĺå¥ij
    0.22
    ãĤ¹ãĤŃ
    0.22
     заÑĤем
    0.20
     tap
    0.20
    å®£ä¼łæ´»åĬ¨
    0.19
    åĪ°åľº
    0.19
    _taken
    0.19
     Converted
    0.19
     огÑĢомн
    0.18
    è¿ħéĢŁ
    0.18
    Activations Density 0.006%

    No Known Activations