© 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. 16958
    Prev
    Next
    INDEX
    Explanations

    free radicals

    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
    å§Ķ
    -0.23
    PLY
    -0.22
    å·®åĪ«
    -0.22
    éĹ»
    -0.22
     Farr
    -0.21
    Fresh
    -0.20
    embr
    -0.20
    被æīĵ
    -0.20
    ç¿İ
    -0.19
    ois
    -0.19
    POSITIVE LOGITS
    æ´»è·ĥ
    0.19
    eton
    0.18
    даÑĢ
    0.18
    çĤĻ
    0.17
     balanced
    0.17
    平衡
    0.17
    _PIN
    0.17
    anges
    0.17
    sss
    0.17
     unchecked
    0.17
    Activations Density 0.033%

    No Known Activations