© 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. 12358
    Prev
    Next
    INDEX
    Explanations

    lean / leaning / leanings

    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
    lest
    -0.18
    ivity
    -0.17
     лиÑĪÑĮ
    -0.17
    uality
    -0.17
    aqu
    -0.16
    窿
    -0.15
    ä¹Ĥ
    -0.15
    ries
    -0.15
    ination
    -0.15
     Ryder
    -0.15
    POSITIVE LOGITS
    erd
    0.18
    ood
    0.18
    er
    0.18
    èĤ©èĨĢ
    0.18
    ings
    0.18
    ģ
    0.17
    ðŁı»
    0.17
    erin
    0.16
    Ļ
    0.16
    eds
    0.16
    Activations Density 0.007%

    No Known Activations