© 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. 15280
    Prev
    Next
    INDEX
    Explanations

    six, 2, 7, Short

    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
    è¿Ļä¸ĢçĤ¹
    -0.22
    ç¾ļ
    -0.21
    è¿Ļæł·ä¸Ģ个
    -0.20
    idual
    -0.20
    åIJĮä¸Ģ个
    -0.19
    ulado
    -0.19
    omination
    -0.19
    uts
    -0.18
    å®Ľå¦Ĥ
    -0.18
    çļĦåij½è¿IJ
    -0.18
    POSITIVE LOGITS
     Finger
    0.20
     finger
    0.20
     lf
    0.19
     Damen
    0.18
     Brom
    0.18
     Birch
    0.18
    ä»İä¸Ń
    0.18
    æĦıæĢĿ
    0.18
    æŦ
    0.17
    lf
    0.17
    Activations Density 0.008%

    No Known Activations