© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    çĵ¢
    -0.22
    american
    -0.21
    istrar
    -0.19
    æĪijè¿ĺæĺ¯
    -0.19
    èįı
    -0.18
    smith
    -0.17
    éĽ¹
    -0.17
    adies
    -0.17
    ä¸ĸ家
    -0.17
    hai
    -0.17
    POSITIVE LOGITS
     Lamar
    0.20
    踪
    0.20
     Hess
    0.20
    该项
    0.20
    åĪĩãĤĮ
    0.19
     Kash
    0.18
    ä¿ĥéĶĢ
    0.18
    olu
    0.18
     Homo
    0.18
    æĬĴ
    0.18
    Activations Density 0.247%

    No Known Activations