© 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. 10755
    Prev
    Next
    INDEX
    Explanations

    triggers, commands

    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
    ¹Ħ
    -0.20
    GIN
    -0.20
    &↵
    -0.20
    ì¹ł
    -0.19
    æľīç§į
    -0.18
    è¾ħ导
    -0.18
    äºĨä¸Ģ声
    -0.18
    ÙĩÙĪ
    -0.18
    å¸Ľ
    -0.17
    Multiplicity
    -0.17
    POSITIVE LOGITS
    åĤį
    0.21
    åıªåī©
    0.20
     Drill
    0.19
    ä»įæľī
    0.19
    åī¯
    0.18
    åıªåī©ä¸ĭ
    0.18
    edList
    0.18
    atement
    0.18
     Consult
    0.17
     Dedicated
    0.17
    Activations Density 0.670%

    No Known Activations