© 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. 15636
    Prev
    Next
    INDEX
    Explanations

    publication and appearance

    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
     sorts
    -0.22
    ives
    -0.19
    sel
    -0.18
     que
    -0.18
     grav
    -0.18
     clones
    -0.18
    ively
    -0.18
     fat
    -0.17
     themselves
    -0.17
     gender
    -0.17
    POSITIVE LOGITS
    äºİ
    0.27
    ä¸ĢåĪĻ
    0.23
    ä¸įè¿ľ
    0.22
    ieu
    0.20
    åİŁæĸĩ
    0.20
     Cellular
    0.20
     ضÙħÙĨ
    0.20
     اÙĦصÙģØŃØ©
    0.19
    ä¸ĵæłı
    0.19
    åı£ç¢ij
    0.19
    Activations Density 0.022%

    No Known Activations