© 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. 14040
    Prev
    Next
    INDEX
    Explanations

    wait a moment

    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
    çľł
    -0.22
    é¢Ķ
    -0.21
    oden
    -0.21
    <quote
    -0.20
    LIK
    -0.19
    å©Ĩå©Ĩ
    -0.19
    顺åĪ©å®ĮæĪIJ
    -0.19
    _lifetime
    -0.19
    æĥľ
    -0.19
    _expect
    -0.19
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.26
    çľĭä¸Ģä¸ĭ
    0.26
    çľĭçľĭ
    0.25
    here
    0.22
    åIJ¬åIJ¬
    0.22
    !
    0.21
    çľĭä¸Ģçľĭ
    0.21
    è¿ĺæľī
    0.20
    è¿ĺæľīä¸Ģ个
    0.19
    ä»ĭç»įä¸Ģä¸ĭ
    0.19
    Activations Density 0.009%

    No Known Activations