© 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. 12968
    Prev
    Next
    INDEX
    Explanations

    teaming up with

    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
    ä½ĵ系建设
    -0.22
    éģij
    -0.20
    å±Ĥåĩº
    -0.20
    destruct
    -0.20
    æľī人说
    -0.19
    èĢģçĪ·
    -0.19
    åıĸå¾Ĺ以åıĬ
    -0.18
    山路
    -0.17
    tern
    -0.17
    æ¨¡æł·
    -0.17
    POSITIVE LOGITS
    èµ·æĿ¥
    0.21
     together
    0.20
     against
    0.20
     to
    0.20
    èĢĮæĪIJ
    0.19
    gether
    0.19
     Against
    0.19
    为
    0.19
    解åĨ³éĹ®é¢ĺ
    0.19
    illet
    0.18
    Activations Density 0.015%

    No Known Activations