© 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. 12124
    Prev
    Next
    INDEX
    Explanations

    thermometer

    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
    IGHT
    -0.19
    ngine
    -0.18
     Indies
    -0.18
    imary
    -0.18
    cripts
    -0.17
    ampa
    -0.17
    -Jun
    -0.17
    tern
    -0.17
    ternal
    -0.17
    iasm
    -0.17
    POSITIVE LOGITS
    ä½ĵ温
    0.21
    ropy
    0.19
     thermometer
    0.19
     çeÅŁit
    0.19
    æ·Ļ
    0.18
    æ¾į
    0.18
    æ£į
    0.18
    CERT
    0.18
    æ£Ĵ
    0.18
    çļĦåĪ°æĿ¥
    0.18
    Activations Density 0.012%

    No Known Activations