© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    said speakers quoting him

    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
    idal
    -0.20
    ги
    -0.20
    æĭĻ
    -0.19
    DataContext
    -0.19
    åı¤ä»£
    -0.19
    éħį
    -0.18
    羣çļĦ
    -0.18
    ptic
    -0.18
    artz
    -0.18
    ówn
    -0.17
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.23
    è´Łè´£
    0.23
    åħ·ä½ĵæĥħåĨµ
    0.21
    éĢıéľ²
    0.21
    ä»ĭç»įäºĨ
    0.20
    à¹ĥหà¸į
    0.20
    çŃ¹å¤ĩ
    0.20
    æĹĮ
    0.20
    åħ·ä½ĵçļĦ
    0.20
    æŃ¤é¡¹
    0.20
    Activations Density 0.044%

    No Known Activations