© 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. 16948
    Prev
    Next
    INDEX
    Explanations

    deals and discounts

    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
    ending
    -0.18
    WARD
    -0.18
    tas
    -0.18
    åĵ¼
    -0.18
    oca
    -0.18
    è°ģçŁ¥
    -0.17
     schön
    -0.17
     Templ
    -0.17
    仪
    -0.17
    ality
    -0.17
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.24
    åĴĮåıijå±ķ
    0.23
    çĬĦ
    0.19
    èĥª
    0.19
    _CID
    0.18
    вÑĥ
    0.18
    /free
    0.18
    PMC
    0.17
    å½ĵäºĭ
    0.17
    hest
    0.17
    Activations Density 0.007%

    No Known Activations