© 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. 13251
    Prev
    Next
    INDEX
    Explanations

    more than one

    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
    们
    -0.24
    NewLabel
    -0.20
    æľĭåıĭ们
    -0.20
    ä¸İåIJ¦
    -0.19
    们çļĦ
    -0.18
    ãģ¾ãģĻ
    -0.18
    ists
    -0.18
    č↵↵
    -0.18
    bsites
    -0.18
    åĢij
    -0.18
    POSITIVE LOGITS
    -half
    0.24
    -way
    0.22
    -ending
    0.20
    -third
    0.20
    -quarter
    0.20
    çŃīåĪ°
    0.19
    ä¸ĢåĽŀäºĭ
    0.19
    à¸Ħะà¹ģà¸Ļ
    0.19
    åľ°æĸ¹
    0.19
    -than
    0.18
    Activations Density 0.022%

    No Known Activations