© 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. 16036
    Prev
    Next
    INDEX
    Explanations

    legal brief

    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
    æ¯ķ
    -0.20
    ISTR
    -0.19
    ä¹ĭåĨħ
    -0.19
    ç»Īç»ĵ
    -0.18
    appropri
    -0.17
    çĭ¼
    -0.17
    ä¸Ńç§ij
    -0.17
    DEX
    -0.17
    xBB
    -0.17
    æ²ĵ
    -0.17
    POSITIVE LOGITS
    adro
    0.21
    åł¡
    0.20
    inet
    0.20
    ked
    0.20
    rik
    0.19
     kep
    0.19
     Koh
    0.17
    à¹ģà¸Ľà¸¥
    0.17
    éĤ£æ®µ
    0.17
    ä½Ĩå®ĥ
    0.17
    Activations Density 0.003%

    No Known Activations