© 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. 11485
    Prev
    Next
    INDEX
    Explanations

    from here or there

    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
    äºĭåıij
    -0.22
    éĩĮéĿ¢æľī
    -0.19
    è¿Ļæł·æīįèĥ½
    -0.19
    äºİæѤ
    -0.19
    icity
    -0.19
    ioned
    -0.19
    åħ¶ä¸Ńæľī
    -0.18
    ãģªãģĮãĤī
    -0.18
    äºĭåħ³
    -0.18
    ä¸ļåĨħ
    -0.18
    POSITIVE LOGITS
    åĩºåıij
    0.27
     onwards
    0.27
    æľĽåİ»
    0.25
    åĨįåĪ°
    0.25
    åħ¥æīĭ
    0.22
     standpoint
    0.22
    延伸
    0.22
    forth
    0.22
     perspective
    0.21
    便åı¯
    0.21
    Activations Density 0.033%

    No Known Activations