© 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. 17126
    Prev
    Next
    INDEX
    Explanations

    screening and its purpose

    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
    æ·±å¤Ħ
    -0.22
    wear
    -0.20
    ä¸ĬçļĦ
    -0.19
    wed
    -0.17
    gre
    -0.16
    ÑijÑĤ
    -0.16
    chaft
    -0.16
    FUL
    -0.16
    çĶŁæĹ¥
    -0.16
    lobs
    -0.16
    POSITIVE LOGITS
    edList
    0.21
    sic
    0.17
    usting
    0.17
    /pre
    0.17
    ute
    0.17
    ä¸İåıijå±ķ
    0.16
    äºĨä¸Ģä¸ĭ
    0.16
    ctions
    0.16
    lems
    0.16
    å·²ä¹ħ
    0.15
    Activations Density 0.016%

    No Known Activations