© 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. 16471
    Prev
    Next
    INDEX
    Explanations

    research and development

    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
    andal
    -0.21
    åĩºåı£
    -0.20
    塬
    -0.19
    åĶ¯
    -0.19
    è¯Ł
    -0.19
    éķ£
    -0.18
    	Run
    -0.18
    åĩºå·®
    -0.18
    andas
    -0.18
    顺
    -0.18
    POSITIVE LOGITS
    å¤ļä½į
    0.20
    åħŃå¹´
    0.19
    ä¸īä½į
    0.19
    åĽĽä½į
    0.19
    åıªçŁ¥éģĵ
    0.19
    vl
    0.17
    åħ³
    0.17
    æķĻçłĶ
    0.17
    pal
    0.17
     Cone
    0.17
    Activations Density 0.002%

    No Known Activations