© 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. 16400
    Prev
    Next
    INDEX
    Explanations

    Monthly Archives: or Category Archives:

    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
    ä¼IJ
    -0.22
    çĿ½
    -0.20
    raft
    -0.19
    æĸĩç«łæĿ¥æºIJ
    -0.19
    éĴ¿
    -0.19
     dém
    -0.18
    IDL
    -0.18
    urf
    -0.18
    溯æºIJ
    -0.18
    olla
    -0.18
    POSITIVE LOGITS
    orer
    0.20
    SCO
    0.19
     freeway
    0.18
    è¿Ļ对
    0.18
    akers
    0.17
    å½Ĺ
    0.17
    alach
    0.17
    _sv
    0.17
    ä¸Ģæł¹
    0.17
    onomies
    0.17
    Activations Density 0.004%

    No Known Activations