© 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. 10928
    Prev
    Next
    INDEX
    Explanations

    number of things

    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
    åĬ²
    -0.23
    Fab
    -0.19
    åĭģ
    -0.18
    ä½ĵéĩı
    -0.18
    ä¸ĢåĪĩéĥ½
    -0.18
    å¤©åĽ½
    -0.18
     lạc
    -0.18
    bidden
    -0.18
    æĥ³åİ»
    -0.18
    ä¸ĭä¸Ģ
    -0.17
    POSITIVE LOGITS
    æľīä¸Ģ次
    0.29
    次æķ°
    0.28
     occasions
    0.26
     ÑģлÑĥÑĩа
    0.25
    ä¸Ģ次
    0.24
    æ¯ı次éĥ½
    0.23
    æĪIJåĬŁçİĩ
    0.23
     cases
    0.21
    æĢ»æķ°
    0.21
    åĩłæ¬¡
    0.21
    Activations Density 0.369%

    No Known Activations