© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17300
    Prev
    Next
    INDEX
    Explanations

    .domain, .bar, .com, .edu

    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
    Negative Logits
    burg
    -0.20
    æĹłæīĢ
    -0.19
    /design
    -0.19
    ä¸Ģæŀļ
    -0.19
    True
    -0.18
    æĬĦ
    -0.17
    _True
    -0.17
    .locals
    -0.17
     IF
    -0.17
     True
    -0.17
    POSITIVE LOGITS
    agn
    0.19
    urname
    0.19
     libero
    0.18
    碰åĪ°
    0.18
    nee
    0.18
    éĥijéĩį
    0.17
    agne
    0.17
    çļĦç§ĺå¯Ĩ
    0.17
    _WS
    0.17
     OVERRIDE
    0.17
    Activations Density 0.002%

    No Known Activations