© 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. 10871
    Prev
    Next
    INDEX
    Explanations

    performance and speed

    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
     civil
    -0.25
    civil
    -0.23
    schedule
    -0.22
    åĩij
    -0.20
     ingen
    -0.20
    itar
    -0.20
    ights
    -0.19
    æģ¬
    -0.19
    åĺĢ
    -0.19
    æ²»
    -0.19
    POSITIVE LOGITS
    æķĪçİĩ
    0.23
    æīĭæĦŁ
    0.22
    åIJ¸çº³
    0.22
    çī¹çĤ¹æĺ¯
    0.22
    å¢ŀéĢŁ
    0.21
    æ¯Ķéĩį
    0.21
    éĩįçĤ¹é¢ĨåŁŁ
    0.21
     пед
    0.21
    èĥ¥
    0.21
     Beginners
    0.20
    Activations Density 0.036%

    No Known Activations