© 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. 12633
    Prev
    Next
    INDEX
    Explanations

    starch or cornstarch

    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
    åij½
    -0.21
    itud
    -0.20
    ihan
    -0.20
     dors
    -0.19
     round
    -0.19
    åĬ«
    -0.19
    æĦīå¿«
    -0.18
    æĪĴ
    -0.18
    亥
    -0.18
    iday
    -0.18
    POSITIVE LOGITS
    润æ»ij
    0.21
    craft
    0.21
    -Ta
    0.20
    稳
    0.20
    æ¸
    0.19
    ç±³ç²ī
    0.19
    ä¾į
    0.19
    OLUM
    0.19
    кÑĢо
    0.19
    ç°Į
    0.18
    Activations Density 0.010%

    No Known Activations