© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    placeholders like ${variable.name} or %parameter%

    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
    è¶Ĭ
    -0.22
    chin
    -0.21
    .deserialize
    -0.19
    è¤
    -0.18
     newObj
    -0.18
    .optimizer
    -0.18
    .prot
    -0.18
    ails
    -0.18
    ubs
    -0.17
    kube
    -0.17
    POSITIVE LOGITS
    åıĺéĩı
    0.30
     variables
    0.26
     reluct
    0.23
    表达
    0.23
    饮çĶ¨
    0.23
     variable
    0.23
    æľĪ份
    0.22
     ë³ĢìĪĺ
    0.21
    -variable
    0.21
     expressions
    0.21
    Activations Density 0.805%

    No Known Activations