© 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. 10893
    Prev
    Next
    INDEX
    Explanations

    This is because

    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
    abouts
    -0.23
    å°ıæŶåīį
    -0.20
    ä¸İæĹ¶ä¿±
    -0.20
    ingleton
    -0.19
    uko
    -0.18
    ç½ijé¦ĸ页
    -0.18
    å°±çŁ¥éģĵ
    -0.18
    åĽ½äºº
    -0.18
    'gc
    -0.18
    jian
    -0.18
    POSITIVE LOGITS
    使å¾Ĺ
    0.29
    ä¸įä»ħ
    0.22
    çĦ¶
    0.21
    atra
    0.20
    èijŃ
    0.20
     necess
    0.19
    alth
    0.19
    åĮħæĭ¬
    0.19
    æĥħåĨµä¸ĭ
    0.19
    åļĵ
    0.19
    Activations Density 0.134%

    No Known Activations