© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12321
    Prev
    Next
    INDEX
    Explanations

    mining and ore processing

    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
     fatty
    -0.21
    檬
    -0.20
    æ²¥
    -0.20
    ful
    -0.19
    olk
    -0.19
    æ°
    -0.19
    iban
    -0.19
    空è°ĥ
    -0.19
    cket
    -0.18
    inflate
    -0.18
    POSITIVE LOGITS
    åĵģä½į
    0.28
    åĨ¶çĤ¼
    0.27
    çŁ¿
    0.27
     ore
    0.27
    çŁ¿å±±
    0.26
    çŁ¿ä¸ļ
    0.26
    åĨ¶éĩij
    0.26
     mining
    0.25
    éĴ¼
    0.24
     Ore
    0.24
    Activations Density 0.043%

    No Known Activations