© 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. 11058
    Prev
    Next
    INDEX
    Explanations

    date or title related

    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
    åħ¬çĶ¨
    -0.21
    oca
    -0.20
    æĺ¯ä»ĸ
    -0.19
    å®
    -0.19
    éļ¾åħ³
    -0.19
    urring
    -0.19
    åĪ¶
    -0.18
    ernote
    -0.18
    inters
    -0.18
    ัย
    -0.18
    POSITIVE LOGITS
    Awesome
    0.21
    次
    0.19
    anol
    0.18
    hopefully
    0.18
    .populate
    0.18
    åĮª
    0.18
     pret
    0.18
    BuildContext
    0.17
    æķ´æ²»
    0.17
     interfer
    0.17
    Activations Density 0.028%

    No Known Activations