© 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. 12019
    Prev
    Next
    INDEX
    Explanations

    selected or chosen for nomination

    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
    å¾Īå¤ļæľĭåıĭ
    -0.24
    chain
    -0.21
    åģļä¸įåĪ°
    -0.20
    æĿĤ
    -0.20
     simple
    -0.20
    å¡Ĩ
    -0.20
    еж
    -0.20
     chain
    -0.19
    ForMember
    -0.19
    è¿ĻäºĽä¸ľè¥¿
    -0.19
    POSITIVE LOGITS
    åIJįåįķ
    0.32
    éĢīå®ļ
    0.26
    åħ¥éĢī
    0.25
    åIJįé¢Ŀ
    0.24
     chosen
    0.23
     selected
    0.23
    selected
    0.23
    ç¿Į
    0.23
    åħ¥åľº
    0.23
    chosen
    0.23
    Activations Density 0.051%

    No Known Activations