© 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. 14961
    Prev
    Next
    INDEX
    Explanations

    gene, trait, or RNA sequence

    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
    âīĤ
    -0.34
    à¦Ī
    -0.32
     désorm
    -0.32
    numerusform
    -0.31
    ×Ĺ×Ļפ×ķש
    -0.31
    	RTLR
    -0.31
    gMaps
    -0.30
    индивид
    -0.30
    ìĸķ
    -0.30
    맴
    -0.29
    POSITIVE LOGITS
    fast
    0.25
    armor
    0.25
    Researchers
    0.23
    link
    0.23
    Jan
    0.23
    ãģĹãģĭãĤĤ
    0.22
    åIJįåı«
    0.22
    ëı¼
    0.22
    Nov
    0.22
    Earlier
    0.22
    Activations Density 0.172%

    No Known Activations