© 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. 15200
    Prev
    Next
    INDEX
    Explanations

    numbers followed by nouns

    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
     паÑĢа
    -0.22
    æ°Ķæ°Ľ
    -0.20
    Terr
    -0.19
    áĥļ
    -0.18
    ·»
    -0.18
     setResult
    -0.18
    Ĭ¶
    -0.18
    åįĹçĵľ
    -0.18
    衬
    -0.17
    ä¸İåħ¶ä»ĸ
    -0.17
    POSITIVE LOGITS
    pes
    0.21
    umen
    0.21
     equally
    0.20
    tre
    0.20
    fold
    0.19
    维度
    0.19
    vil
    0.19
    ä¸Ģä½ĵ
    0.18
    ain
    0.18
    ston
    0.18
    Activations Density 0.056%

    No Known Activations