© 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. 10604
    Prev
    Next
    INDEX
    Explanations

    click anywhere on

    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
    ç¢ī
    -0.20
    çĵ£
    -0.19
    ä¸Ģè¾ĪåŃIJ
    -0.18
    à¹Ģà¸Ĺ
    -0.18
    .bp
    -0.18
    骥
    -0.18
    èĻļ
    -0.18
    ibus
    -0.18
    candidate
    -0.17
    ROUT
    -0.17
    POSITIVE LOGITS
    ,www
    0.21
    ä¼łéĶĢ
    0.20
    触åıij
    0.19
    èĢ½
    0.19
    çĶŁæĪIJ
    0.18
    幡
    0.18
    æĢħ
    0.18
    pii
    0.18
     ÑģоÑģÑĤ
    0.17
    触
    0.17
    Activations Density 0.046%

    No Known Activations