© 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. 10616
    Prev
    Next
    INDEX
    Explanations

    don't understand, see, know, want, agree

    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
    Not in Any Lists

    No Comments

    Negative Logits
    pres
    -0.22
    trial
    -0.21
     pres
    -0.20
    Pres
    -0.20
    åij£
    -0.20
    çħŀ
    -0.19
    è·ijåİ»
    -0.19
    ëĨĢ
    -0.19
     resp
    -0.18
     Pres
    -0.18
    POSITIVE LOGITS
    å¸ĮæľĽå¤§å®¶
    0.23
    çĽ¸ä¿¡
    0.22
    æĢ»è§īå¾Ĺ
    0.21
    inue
    0.20
    èĥ½çľĭåĩº
    0.20
    æĦŁè§īåĪ°
    0.20
    认为
    0.20
    覺å¾Ĺ
    0.19
     believe
    0.19
    çĽ¸ä¿¡å¤§å®¶
    0.19
    Activations Density 0.058%

    No Known Activations