© 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. 12272
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    èĨº
    -0.22
    ESS
    -0.21
    é¡¿
    -0.21
     stride
    -0.20
    æĻ®æĥł
    -0.20
     ÑģоÑģÑĤоиÑĤ
    -0.20
    æľīèĩªå·±çļĦ
    -0.20
    ãģĻ
    -0.20
    ons
    -0.20
    åį°è±¡æ·±åĪ»
    -0.19
    POSITIVE LOGITS
    	RTLR
    0.28
    incess
    0.25
    ìĸķ
    0.24
    $fdata
    0.22
    usher
    0.22
    azzi
    0.22
    ﹩
    0.22
    'http
    0.21
    CALLTYPE
    0.21
    맴
    0.20
    Activations Density 0.160%

    No Known Activations