© 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. 13838
    Prev
    Next
    INDEX
    Explanations

    numbers before runs or hits

    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
    大èħ¿
    -0.23
    佬
    -0.21
    utow
    -0.20
    èĭķ
    -0.20
    odom
    -0.20
    åĿij
    -0.19
    @update
    -0.19
     ÐIJлекÑģан
    -0.19
    à¸Ħà¸ĵะà¸ģรรม
    -0.19
    à¹Ĥรà¸ĩà¸ŀยา
    -0.19
    POSITIVE LOGITS
    åĺı
    0.21
    eph
    0.20
    èĶĵ
    0.18
    ãĥķãĤ§
    0.18
    çķ¥æľī
    0.18
    å°ijéĩı
    0.18
    ç¥ī
    0.18
    ael
    0.18
    æĶ¶å®ĺ
    0.18
     но
    0.18
    Activations Density 0.002%

    No Known Activations