© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    Mac

    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
    æĦŁ
    -0.20
    æ¯ķ
    -0.19
    æijĨåľ¨
    -0.18
    è·ŁæĪij
    -0.18
    åĬ¨æijĩ
    -0.18
    润
    -0.18
     اÙĦع
    -0.18
     Farms
    -0.18
    æ¿Ģèµ·
    -0.18
     collateral
    -0.17
    POSITIVE LOGITS
    çĭ¬å®¶
    0.27
    è¯Ŀè¯ŃæĿĥ
    0.23
    æ·±çŁ¥
    0.22
    owns
    0.22
    åĽ½å®¶æłĩåĩĨ
    0.21
     pione
    0.21
     кÑĢÑĥп
    0.21
    ä¸įä»ħå¦ĤæѤ
    0.21
    çĭĤ
    0.20
    è¿Ļç±»
    0.20
    Activations Density 0.071%

    No Known Activations