© 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. 14942
    Prev
    Next
    INDEX
    Explanations

    man or woman

    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
    icip
    -0.20
    æĻ®åıĬ
    -0.19
    å¾ĹåĪ°æľīæķĪ
    -0.19
    鼶ç¢İ
    -0.19
    apan
    -0.19
    ä¸ŃåĽ½çī¹èī²
    -0.18
    鸦
    -0.18
    çĸ³
    -0.18
    åĴĮæĶ¯æĮģ
    -0.18
    éĽĨä¸Ńåľ¨
    -0.18
    POSITIVE LOGITS
    hood
    0.25
    å§ĵåIJį
    0.20
    人éĥ½
    0.19
     male
    0.19
     whose
    0.18
    åĮĸçļĦ
    0.18
     silhouette
    0.18
    ne
    0.17
    çĶ·åŃIJ
    0.17
     who
    0.17
    Activations Density 0.040%

    No Known Activations