© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14602
    Prev
    Next
    INDEX
    Explanations

    reports and rumors

    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
    å½ĵä¹ĭæĹłæĦ§
    -0.18
    ì²´
    -0.18
     helicopt
    -0.18
    çĶ¨èĩªå·±çļĦ
    -0.17
    ::__
    -0.17
    åĩŃçĿĢ
    -0.17
     overwhel
    -0.17
    æĶ¾æīĭ
    -0.17
    urst
    -0.16
     explos
    -0.16
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.34
    æ¶Īæģ¯ç§°
    0.27
     rumors
    0.25
     rumours
    0.23
    åªĴä½ĵæĬ¥éģĵ
    0.23
    å·²ä¹ħ
    0.23
    沸
    0.22
     rằng
    0.22
     reports
    0.22
    æĬ¥éģĵ称
    0.21
    Activations Density 0.053%

    No Known Activations