© 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. 12216
    Prev
    Next
    INDEX
    Explanations

    version identifiers

    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
     Ñģог
    -0.20
    ä¸İåħ¶ä»ĸ
    -0.19
    ÑģлÑĥÑĪа
    -0.19
    èĵ¬
    -0.18
    é¥Ń
    -0.18
    éŀŃ
    -0.17
    пÑĢоÑĦеÑģÑģионал
    -0.17
    Attrib
    -0.17
     Examiner
    -0.17
    _POLL
    -0.17
    POSITIVE LOGITS
    ering
    0.29
    ible
    0.23
    ress
    0.20
    enci
    0.20
    er
    0.20
    åĮĸ
    0.19
    ation
    0.19
    Fri
    0.19
    eration
    0.19
    ä»»ä½ķå½¢å¼ı
    0.18
    Activations Density 0.096%

    No Known Activations