© 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. 10856
    Prev
    Next
    INDEX
    Explanations

    addressing issues or problems

    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
    说çļĦè¯Ŀ
    -0.19
    loff
    -0.19
    akov
    -0.19
    çĸ¡
    -0.18
    éĢīæĭ
    -0.18
    åıijå±ķåīįæĻ¯
    -0.17
    ously
    -0.16
    Ø°Ùĩب
    -0.16
    arris
    -0.16
    æĥ³èµ·æĿ¥
    -0.16
    POSITIVE LOGITS
    è¿Ļ个éĹ®é¢ĺ
    0.28
    çªģåĩºéĹ®é¢ĺ
    0.26
    è¿ĻäºĽéĹ®é¢ĺ
    0.22
     issues
    0.21
    妤
    0.21
    æѤäºĭ
    0.20
    oling
    0.19
    ìĤ¬íķŃ
    0.19
    ioned
    0.18
     конкÑĢеÑĤ
    0.18
    Activations Density 0.036%

    No Known Activations