© 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. 16207
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åIJĪéĢĤçļĦ
    -0.20
    ä¸ĬéŨ
    -0.20
    /div
    -0.20
     tre
    -0.19
    endum
    -0.19
    èµ·æĿ¥
    -0.19
    çļĦè¯Ŀ
    -0.19
    ARGV
    -0.19
     scal
    -0.18
     autop
    -0.18
    POSITIVE LOGITS
    è¿ĻåĿĹ
    0.20
    rig
    0.19
    BOR
    0.17
    Îŀ
    0.17
    ä¿¡æģ¯åħ¬å¼Ģ
    0.17
    æĦį
    0.17
    evin
    0.17
    OSE
    0.16
    etical
    0.16
    (:,:,
    0.16
    Activations Density 0.000%

    No Known Activations