© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15271
    Prev
    Next
    INDEX
    Explanations

    true or false values

    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
    mPid
    -0.20
    èIJ
    -0.19
    bard
    -0.19
    èįŁ
    -0.19
    licken
    -0.19
    <typeof
    -0.18
    lop
    -0.18
    ENGINE
    -0.18
    LIBINT
    -0.18
    åľĨ满å®ĮæĪIJ
    -0.18
    POSITIVE LOGITS
    False
    0.30
     True
    0.29
    True
    0.28
    =true
    0.28
     False
    0.28
     false
    0.28
    /false
    0.28
    =True
    0.27
    :false
    0.27
     true
    0.27
    Activations Density 0.285%

    No Known Activations