© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 12458
    Prev
    Next
    INDEX
    Explanations

    Key _car ) 1 0 second , );

    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
    erland
    -0.27
    	RTLR
    -0.26
    iect
    -0.24
    ë§´
    -0.23
    riba
    -0.23
    uling
    -0.22
    ìĸķ
    -0.22
    repid
    -0.22
    glomer
    -0.22
    iben
    -0.22
    POSITIVE LOGITS
    æĢ»èµĦ产
    0.23
    çī¹èī²å°ıéķĩ
    0.23
    纳æĸ¯
    0.22
    ãĥ¢ãĥĩ
    0.21
     snap
    0.20
    å±Ĥåĩºä¸į
    0.20
    åħħå½ĵ
    0.20
    trait
    0.20
    çī¹è´¨
    0.20
    finish
    0.20
    Activations Density 0.075%

    No Known Activations