© 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. 12698
    Prev
    Next
    INDEX
    Explanations

    sensor applications and systems

    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
    å·´å·´
    -0.19
    ãĤĤãģĨ
    -0.18
    -Russian
    -0.18
    ðŁı»
    -0.17
    èĸ®
    -0.17
    OnError
    -0.17
    äºĨä¸Ģ份
    -0.16
    aways
    -0.16
    tempt
    -0.16
    ty
    -0.16
    POSITIVE LOGITS
    ULAR
    0.20
    ิà¸ģ
    0.17
    less
    0.16
     behalf
    0.15
    æİ¢
    0.15
    ÙĬÙĦ
    0.15
    ium
    0.15
     quat
    0.14
    ing
    0.14
    ial
    0.14
    Activations Density 0.056%

    No Known Activations