© 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. 16166
    Prev
    Next
    INDEX
    Explanations

    BlackBerry

    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
    _phys
    -0.20
    ãģĺ
    -0.18
    warn
    -0.18
    çĪµ
    -0.18
    BMW
    -0.18
    ä¸ªé¡¹çĽ®
    -0.18
    æ¸ħçIJĨ
    -0.18
    æİ®
    -0.17
    èݳ
    -0.17
    uration
    -0.17
    POSITIVE LOGITS
    åħ¬åı¸å°Ĩ
    0.20
    addin
    0.20
    åŀĤ
    0.20
    _sec
    0.19
    å¼ĢåĪĽ
    0.19
    éĶĻè¿ĩäºĨ
    0.19
    å¿Ĺ强
    0.19
    èµĸ以
    0.19
    ®
    0.18
     prec
    0.18
    Activations Density 0.004%

    No Known Activations