© 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. 10772
    Prev
    Next
    INDEX
    Explanations

    Read more

    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
    alic
    -0.22
    "+"
    -0.21
    å¨ģæħij
    -0.20
    æīĵäºĨ
    -0.18
    åĪ
    -0.18
     distinguished
    -0.18
    缴æݥ影åĵį
    -0.18
     Dü
    -0.17
    ç¤ĵ
    -0.17
    elier
    -0.17
    POSITIVE LOGITS
    ç¶ļãģį
    0.19
    碧
    0.18
    åŃIJéĩĮ
    0.18
     unfinished
    0.18
    æĢ»ä¹ĭ
    0.18
    icit
    0.18
    heits
    0.18
    åĴĢ
    0.18
    SizeMode
    0.17
    åĻİ
    0.17
    Activations Density 0.092%

    No Known Activations