© 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. 16432
    Prev
    Next
    INDEX
    Explanations

    time or end of event

    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
    çĸı
    -0.22
    æĬĸ
    -0.22
    æ¯ķä¸ļ
    -0.20
    å±IJ
    -0.19
     Trev
    -0.19
    alter
    -0.19
    led
    -0.19
    对çĿĢ
    -0.19
    çĽĨ
    -0.19
     alteration
    -0.19
    POSITIVE LOGITS
    æĶ¶çĽĺ
    0.25
    çķĻä¸ĭ
    0.23
    åīįä¸ī
    0.21
    çķĻç»Ļ
    0.21
    ä¸įçķĻ
    0.21
    åħ³éŨ
    0.21
    ç»ĵå°¾
    0.21
    æĶ¾åѦ
    0.20
    å²ģ
    0.20
    ä¼ijæģ¯
    0.20
    Activations Density 0.114%

    No Known Activations