© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences

    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
     rail
    -0.22
     bibliography
    -0.21
     greatest
    -0.20
    bib
    -0.20
     ro
    -0.19
     poor
    -0.18
     legend
    -0.18
    ide
    -0.18
    osis
    -0.18
     ke
    -0.18
    POSITIVE LOGITS
    å¦Ĥæŀľçݩ家
    0.22
    æĢ»èĢĮè¨Ģ
    0.20
    çĻ¾åĪĨçĻ¾
    0.19
    ç°¡
    0.19
    åĨħåĪĨæ³Į
    0.19
    涮
    0.19
    龸
    0.19
    çݩ家æĿ¥è¯´
    0.19
    ðŁĺĵ
    0.19
    æ°¸ä¸į
    0.19
    Activations Density 0.280%

    No Known Activations