© 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. 10331
    Prev
    Next
    INDEX
    Explanations

    ancestors and ancestry

    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
    æİ·
    -0.17
    antha
    -0.17
    ä¸į失
    -0.16
    è§Ħ模æľĢ大
    -0.16
    -sized
    -0.15
    _iff
    -0.15
    onnen
    -0.15
     зани
    -0.15
    processable
    -0.14
    /he
    -0.14
    POSITIVE LOGITS
    stry
    0.21
    oll
    0.20
    gram
    0.20
    GRAM
    0.19
    LL
    0.19
    less
    0.18
    oring
    0.18
    èĢĺ
    0.17
    ãģ¾ãģĦ
    0.17
    ä¸įæĺİ
    0.17
    Activations Density 0.005%

    No Known Activations