© 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. 15478
    Prev
    Next
    INDEX
    Explanations

    Ecuador, differentiation, modify, mitochondrial

    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
    ä¿¡æģ¯åıijå¸ĥ
    -0.20
    çł»
    -0.19
    ouver
    -0.19
     Minds
    -0.18
     bat
    -0.18
    éĢĤå½ĵ
    -0.18
     ÑģÑĭÑĢ
    -0.17
    éĢĤ度
    -0.17
    öffent
    -0.17
    ONSE
    -0.17
    POSITIVE LOGITS
    严å¯Ĩ
    0.20
    èĩĢ
    0.20
    å²ģ以ä¸ĭ
    0.20
    æĮģãģ¡
    0.19
    æķijæ²»
    0.18
    èģĸ
    0.18
    åľ£
    0.18
    湫
    0.18
    æĿľ
    0.17
    åĿ©
    0.17
    Activations Density 0.001%

    No Known Activations