© 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. 13216
    Prev
    Next
    INDEX
    Explanations

    containers for items

    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
    sted
    -0.20
    _execute
    -0.19
    红楼
    -0.19
    çªĹå¤ĸ
    -0.18
    iring
    -0.18
    _pat
    -0.18
    è°¤
    -0.18
     telesc
    -0.17
     ire
    -0.17
    -heavy
    -0.17
    POSITIVE LOGITS
    å¸ĤåĢ¼
    0.20
    pet
    0.20
    éĹŃ
    0.20
    Shared
    0.20
    ä¾Ľ
    0.19
    arat
    0.19
    ä¸ĵéĹ¨ä¸º
    0.19
    quals
    0.19
    mts
    0.19
    æľŁéĻIJ
    0.19
    Activations Density 0.039%

    No Known Activations