© 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. 16046
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

    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
     reinforcement
    -0.21
    ä»ĬæĻļ
    -0.20
    åĪĥ
    -0.20
    岫
    -0.19
    åħīæºIJ
    -0.19
    åĦĨ
    -0.18
    度è¿ĩ
    -0.18
    çĪ±ä½ł
    -0.18
    å·²æĺ¯
    -0.18
     gone
    -0.17
    POSITIVE LOGITS
    endor
    0.24
    åŃĹåı·
    0.23
    _dash
    0.19
    imiter
    0.19
     Hancock
    0.19
    Merchant
    0.18
    lator
    0.18
    Alexander
    0.18
    ä¸ĵéŨ
    0.18
    óa
    0.17
    Activations Density 0.007%

    No Known Activations