© 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. 11340
    Prev
    Next
    INDEX
    Explanations

    legal definitions and conditions

    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
    å©ŀ
    -0.26
    çĿİ
    -0.25
    åªĸ
    -0.24
    éķ©
    -0.24
    iron
    -0.23
    ä¢
    -0.23
    å¾Īå¿«
    -0.23
    big
    -0.23
    iegel
    -0.23
     half
    -0.23
    POSITIVE LOGITS
    åľ¨çݩ家ä¸Ń
    0.34
    欸
    0.29
    æĺİç¡®è§Ħå®ļ
    0.28
    åĶ·
    0.26
    è§Ħå®ļçļĦ
    0.26
    åĴ©
    0.25
     subparagraph
    0.25
    çŀĭ
    0.25
     Fucked
    0.25
    åij£
    0.25
    Activations Density 0.040%

    No Known Activations