© 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. 11840
    Prev
    Next
    INDEX
    Explanations

    « quotes

    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
    asan
    -0.20
    妾
    -0.19
    iseum
    -0.19
    é¢Ľ
    -0.19
    sex
    -0.19
    imest
    -0.19
    rics
    -0.18
    Stuff
    -0.17
    鸾
    -0.17
    à¹Į
    -0.17
    POSITIVE LOGITS
    äºĨä¸Ģæī¹
    0.20
    алÑĮ
    0.19
    -DD
    0.18
    é£İåIJ¹
    0.18
     пеÑĢв
    0.17
    åīį段æŶéĹ´
    0.16
    олÑĮко
    0.16
    æī¹æ¬¡
    0.16
    .tp
    0.16
    æѤåīį
    0.16
    Activations Density 0.018%

    No Known Activations