© 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. 12093
    Prev
    Next
    INDEX
    Explanations

    academic levels and years

    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
    illet
    -0.20
    .dk
    -0.20
    å¿«
    -0.20
     fast
    -0.20
    让人们
    -0.19
    Nam
    -0.19
    æī¯
    -0.19
    åĿ
    -0.18
    fast
    -0.18
    æīĭ
    -0.18
    POSITIVE LOGITS
    -level
    0.26
    å±Ĥ次
    0.25
     level
    0.24
    ãĥ¬ãĥĻãĥ«
    0.23
    .level
    0.23
    level
    0.23
     nÃŃvel
    0.22
    åıĬ以ä¸Ĭ
    0.22
    级
    0.21
    	level
    0.21
    Activations Density 0.006%

    No Known Activations