© 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. 10462
    Prev
    Next
    INDEX
    Explanations

    appetizing food, accessories, or sequels

    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
    èĭ±æīį
    -0.20
    bows
    -0.19
    ocs
    -0.18
    å½ĵåīįä½įç½®
    -0.18
    achinery
    -0.18
    è¡£
    -0.17
    ahoma
    -0.17
    ç©¿è¡£
    -0.17
    allis
    -0.17
    aneous
    -0.17
    POSITIVE LOGITS
    çĤ¸
    0.22
    å´Ĩ
    0.21
    ãĥ³ãĥĪ
    0.20
    rete
    0.20
     exploding
    0.19
    olle
    0.19
    åĦ¿
    0.19
    éŃģ
    0.18
    大åħ¨
    0.18
    件
    0.18
    Activations Density 0.001%

    No Known Activations