© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15189
    Prev
    Next
    INDEX
    Explanations

    post, editions, question, route, server, bow

    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
    å±ĭéĩĮ
    -0.20
    ç¼ķ
    -0.20
     intermittent
    -0.19
    æĢĤ
    -0.19
    ä¸Ģå¹ķ
    -0.19
    æ¦Ħ
    -0.19
    å²Į
    -0.19
    åŃĸ
    -0.19
    åµĺ
    -0.18
    ObjectName
    -0.18
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.31
     моÑīн
    0.25
    å¦Ĥ
    0.25
     ÐĶмиÑĤÑĢ
    0.24
    以
    0.24
     PaÅĦstwo
    0.23
     пÑĢиÑıÑĤн
    0.23
     наÑĢко
    0.23
    пÑĢоÑĦеÑģÑģионал
    0.23
    æĿ¥
    0.23
    Activations Density 0.291%

    No Known Activations