© 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. 10499
    Prev
    Next
    INDEX
    Explanations

    recommendations, suggestions, propositions

    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
    å¯ĵ
    -0.20
    åı°
    -0.20
    ä½ľå®¶
    -0.19
     Mara
    -0.19
     DOMAIN
    -0.19
    regist
    -0.18
    éĽª
    -0.18
    peak
    -0.18
    åĪ¶åĵģ
    -0.18
    çĻ»
    -0.17
    POSITIVE LOGITS
    ç¼ł
    0.20
     vent
    0.20
    对èĩªå·±
    0.19
    转åħ¥
    0.19
    .wind
    0.18
    _tolerance
    0.18
     Vent
    0.18
    ERO
    0.18
    åĴ¬
    0.18
    è¦ģæ±Ĥ
    0.18
    Activations Density 0.254%

    No Known Activations