© 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. 13707
    Prev
    Next
    INDEX
    Explanations

    2d

    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
    ï¸
    -0.20
    EEK
    -0.19
    uml
    -0.18
    éĢĶä¸Ń
    -0.18
    worthy
    -0.18
    spb
    -0.18
    ivor
    -0.18
    æĶ¶åıĹ
    -0.18
    ieri
    -0.18
    è°¯
    -0.17
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.22
    å¹³éĿ¢
    0.22
    çīĩéĿ¢
    0.19
     plane
    0.18
    æĬĢèĥ½åŁ¹è®Ń
    0.18
     symbols
    0.18
    ollar
    0.18
    çľĭä¼¼
    0.17
    ¹
    0.17
    andom
    0.17
    Activations Density 0.089%

    No Known Activations