© 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. 14526
    Prev
    Next
    INDEX
    Explanations

    age of

    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
    ä¸įä¿¡
    -0.20
    bare
    -0.20
    osl
    -0.19
    lya
    -0.19
    FFF
    -0.18
    äºĨä¸ĭæĿ¥
    -0.18
    itted
    -0.18
    窨
    -0.18
    å°±çŁ¥éģĵ
    -0.18
    RAFT
    -0.18
    POSITIVE LOGITS
    稼
    0.20
    _bh
    0.19
    ç£ķ
    0.19
    çĬ¹
    0.18
    æķ´å¤©
    0.18
     Timeout
    0.18
    âķIJ
    0.18
    å®ŀäºĭæ±Ĥæĺ¯
    0.18
    移交
    0.18
    èĬ³
    0.18
    Activations Density 0.014%

    No Known Activations