© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15002
    Prev
    Next
    INDEX
    Explanations

    closer look

    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
    manship
    -0.22
    eer
    -0.20
    å¤ĸèµĦ
    -0.19
    ç²Ł
    -0.18
    é£İåIJ¹
    -0.18
    åī¡
    -0.18
    oire
    -0.17
    çĺ¾
    -0.17
    è¶³å¤Ł
    -0.17
    磶
    -0.17
    POSITIVE LOGITS
    çļĦèĦļæŃ¥
    0.20
    elines
    0.19
    dds
    0.17
    mods
    0.17
    uries
    0.17
    æİ¥è¿ij
    0.16
    onders
    0.16
    èµ°è¿ij
    0.16
    daq
    0.16
    ######
    0.16
    Activations Density 0.009%

    No Known Activations