© 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. 15499
    Prev
    Next
    INDEX
    Explanations

    original post message Archives

    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
    åijĹ
    -0.20
    éĻĦ
    -0.18
     inn
    -0.18
    iam
    -0.18
    饮
    -0.18
    rok
    -0.17
    宦
    -0.17
    ç¶ļ
    -0.17
     пÑĢежде
    -0.17
    IVERS
    -0.17
    POSITIVE LOGITS
    ç»ıèIJ¥æ´»åĬ¨
    0.20
    åįĹè·¯
    0.20
    ä¸Ńåħ³
    0.19
    èĤ¡æ°ij
    0.18
    éĥ¾
    0.18
    ç¼ī
    0.18
    çĤ¬
    0.17
    SMART
    0.17
    ething
    0.17
    peak
    0.17
    Activations Density 0.175%

    No Known Activations