© 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. 11564
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Garner
    -0.21
    è¡Įä¸ļä¸Ń
    -0.21
    гаÑĢ
    -0.21
    缸æ¯Ķ
    -0.20
    éĵĨ
    -0.20
    ç¾ŀ
    -0.19
    mony
    -0.19
    竣工
    -0.18
     RID
    -0.18
    dex
    -0.18
    POSITIVE LOGITS
    ç¥Ŀ
    0.20
    éķij
    0.19
    éĻĪåĪĹ
    0.19
    èįīåİŁ
    0.18
    å¸ĥç½®
    0.18
     verdad
    0.18
    plain
    0.18
    åģľä¸ĭæĿ¥
    0.18
    ç»´å¥ĩ
    0.17
    ¡°
    0.17
    Activations Density 0.000%

    No Known Activations