© 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. 11133
    Prev
    Next
    INDEX
    Explanations

    performance and processing

    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
    ä¿¡ä»»
    -0.24
     trust
    -0.21
    æīĭåĨĮ
    -0.20
     mutually
    -0.19
    icont
    -0.19
     unsafe
    -0.18
     trusted
    -0.18
    éļ
    -0.18
    aked
    -0.18
     prick
    -0.18
    POSITIVE LOGITS
    é«ĺæĢ§èĥ½
    0.27
    æIJŃè½½
    0.22
    æľįåĬ¡èĥ½åĬĽ
    0.22
    çĶ¨éĢĶ
    0.22
    æµģçķħ
    0.22
    主è¦ģçĶ¨äºİ
    0.22
    çĵ¶é¢Ī
    0.21
    -heavy
    0.21
    æµıè§Ī
    0.21
    åĩºç§Ł
    0.21
    Activations Density 0.079%

    No Known Activations