© 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. 14343
    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
    çĻ½é©¬
    -0.22
    èijµ
    -0.21
    æŃ£è§Ħ
    -0.21
    æ·Į
    -0.20
    è¾Ľ
    -0.19
    强度
    -0.19
    ä¸¥æł¼çļĦ
    -0.19
     intensive
    -0.19
     gest
    -0.19
    ZONE
    -0.18
    POSITIVE LOGITS
    Emb
    0.20
    åĽŀ
    0.20
    è¯ķåį·
    0.19
    isoft
    0.18
     Weinstein
    0.18
    æ³Ħ
    0.18
    edm
    0.18
    -write
    0.18
    çĩ
    0.18
     Cannon
    0.18
    Activations Density 0.000%

    No Known Activations