© 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. 17148
    Prev
    Next
    INDEX
    Explanations

    Patchogue, News, Athletic, Press

    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
    DMI
    -0.19
    çľŁç©º
    -0.19
    OTES
    -0.18
    jective
    -0.18
    åĨħéĻĨ
    -0.18
    åºĶä»ĺ
    -0.18
    çīĪæĿĥ声æĺİ
    -0.18
    æĩĴå¾Ĺ
    -0.17
    çĦ°
    -0.17
    oose
    -0.17
    POSITIVE LOGITS
    åħ±äº§
    0.21
    èµį
    0.21
    мел
    0.20
     Lub
    0.20
    飨
    0.19
    [__
    0.18
     Reception
    0.18
    ÑĩаÑĤ
    0.18
    dings
    0.18
    Separated
    0.18
    Activations Density 0.001%

    No Known Activations