© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    numbers and units like %

    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
    rina
    -0.21
    adin
    -0.20
    é¢ĺ主
    -0.20
    èħĬ
    -0.20
    pawn
    -0.19
    常æĢģ
    -0.19
     August
    -0.18
     Trot
    -0.18
    jas
    -0.18
    çĤķ
    -0.18
    POSITIVE LOGITS
    åIJĮç±»
    0.28
    çİĩè¾¾
    0.26
    é«ĺè¾¾
    0.24
    å¤ļè¾¾
    0.23
    ä¼ĺäºİ
    0.22
     compared
    0.20
    è®°å¿ĨåĬĽ
    0.20
    媲
    0.20
    оÑģÑĤÑĮ
    0.20
    åĢį
    0.20
    Activations Density 0.032%

    No Known Activations