© 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. 16161
    Prev
    Next
    INDEX
    Explanations

    display

    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
    çŁ¿æ³īæ°´
    -0.24
    /rfc
    -0.20
    bane
    -0.20
    bildung
    -0.20
    häuser
    -0.19
    emade
    -0.19
    éĵ¾æĿ¡
    -0.19
    ðŁı»
    -0.19
    èķĻ
    -0.19
    ungen
    -0.19
    POSITIVE LOGITS
     display
    0.24
     ÑįкÑĢан
    0.22
    screen
    0.22
    size
    0.21
     screen
    0.21
    æŀģ
    0.21
    	screen
    0.21
    åĪĨ辨çİĩ
    0.21
    亮度
    0.21
    å±ıå¹ķ
    0.20
    Activations Density 0.043%

    No Known Activations