© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    omitted, removed, missing, loss

    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
    rig
    -0.19
     disag
    -0.19
    ç´¯äºĨ
    -0.18
    æħ¢
    -0.18
    atri
    -0.18
    üs
    -0.18
     Prime
    -0.18
    atories
    -0.18
    è°´
    -0.18
    itzer
    -0.18
    POSITIVE LOGITS
    ä¸įè§ģäºĨ
    0.32
    æİīäºĨ
    0.31
    æ¶Ī失äºĨ
    0.30
     altogether
    0.29
    æ¶Ī失
    0.26
    缺å¸Ń
    0.25
    ä¸įè§ģ
    0.24
     omission
    0.24
    æĹłå½¢
    0.24
    omm
    0.23
    Activations Density 0.300%

    No Known Activations