© 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. 12183
    Prev
    Next
    INDEX
    Explanations

    data interchange format

    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
     ÐIJлекÑģан
    -0.24
    迹
    -0.22
     Chop
    -0.19
     relevant
    -0.19
    unts
    -0.18
    大ä¼ļ
    -0.18
     dot
    -0.18
    chers
    -0.18
     vo
    -0.18
     Eins
    -0.17
    POSITIVE LOGITS
     задаÑĩ
    0.19
    uci
    0.19
    æ£
    0.19
    _ratings
    0.19
     бÑĥкв
    0.18
    isen
    0.18
    çĨĺ
    0.18
    æ½ĭ
    0.18
    _gamma
    0.18
    иÑĤелÑĮ
    0.17
    Activations Density 0.408%

    No Known Activations