© 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. 11495
    Prev
    Next
    INDEX
    Explanations

    Yosemite, smartphone, Circuit

    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
    rees
    -0.19
    åĵį
    -0.18
    驼
    -0.18
    庵
    -0.18
    龸æ°Ķ
    -0.18
    大æłij
    -0.17
    åĮĹ京æŶéĹ´
    -0.17
    nam
    -0.17
    缸èģļ
    -0.16
    lyn
    -0.16
    POSITIVE LOGITS
    åĨĴ
    0.21
    çļĦçľ¼
    0.19
    itude
    0.19
     sud
    0.18
    æ°Ľ
    0.18
    åĴİ
    0.18
    ouri
    0.17
    ymoon
    0.17
    éĥ¢
    0.17
    oure
    0.17
    Activations Density 0.026%

    No Known Activations