© 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. 14280
    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
    æł¸éħ¸
    -0.21
    æ§
    -0.20
     tumble
    -0.19
    ventions
    -0.19
     Cream
    -0.19
    gregate
    -0.19
    ekte
    -0.18
    å¤ķéĺ³
    -0.18
    ilate
    -0.18
    Claim
    -0.18
    POSITIVE LOGITS
    æĢľ
    0.23
    åħ¼èģĮ
    0.21
    çĻ»
    0.21
    å¯Ħ
    0.20
    -aut
    0.19
    FUL
    0.19
    hon
    0.19
    اش
    0.19
    绿èī²éĢļéģĵ
    0.19
    éĤ£äºĽ
    0.18
    Activations Density 0.000%

    No Known Activations