© 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. 11823
    Prev
    Next
    INDEX
    Explanations

    substrate

    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
    主è§Ĥ
    -0.21
    åĴĮæľįåĬ¡
    -0.20
    è¾Ł
    -0.20
    /navbar
    -0.20
     Alam
    -0.20
    åĽłæŀľ
    -0.19
    èĭ«
    -0.19
    igham
    -0.19
    缤纷
    -0.19
    éĢĥçĶŁ
    -0.18
    POSITIVE LOGITS
    å·²ç»ıæľī
    0.30
     existing
    0.29
     underlying
    0.29
    å·²æľī
    0.28
    existing
    0.28
    substr
    0.27
    åºķå±Ĥ
    0.27
    ç²Ĺç³Ļ
    0.26
     substrate
    0.26
    éĭª
    0.26
    Activations Density 0.336%

    No Known Activations