© 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. 10529
    Prev
    Next
    INDEX
    Explanations

    names of people mentioned

    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
    羣æŃ£
    -0.21
    history
    -0.21
    æĢ§æł¼
    -0.20
    åĪĽä½ľèĢħ
    -0.20
    对èĩªå·±
    -0.20
    æĦŁè§īèĩªå·±
    -0.20
    åĪ»èĭ¦
    -0.19
    _syntax
    -0.19
    åĪĽä½ľ
    -0.19
    _cases
    -0.19
    POSITIVE LOGITS
    çĿ£åĬŀ
    0.24
    åı£å¾Ħ
    0.24
    åĬŀåħ¬åİħ
    0.23
     Respond
    0.22
    è§Ĩå¯Ł
    0.21
    opaque
    0.21
    ammu
    0.21
    å·¡è§Ĩ
    0.20
    æ°ĶåĢĻåıĺåĮĸ
    0.20
    å®ĺåijĺ
    0.20
    Activations Density 0.067%

    No Known Activations