© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12232
    Prev
    Next
    INDEX
    Explanations

    conquer or conquered

    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¸Ģ个éĹ®é¢ĺ
    -0.17
    æµģåŁŁ
    -0.16
    sville
    -0.16
    kehr
    -0.16
    lessly
    -0.16
    illé
    -0.16
    voke
    -0.16
    è°
    -0.15
    åĴª
    -0.15
    age
    -0.15
    POSITIVE LOGITS
    eur
    0.19
    eer
    0.19
    edException
    0.17
     поÑĤом
    0.17
    èĢħçļĦ
    0.17
    (es
    0.17
    esimal
    0.16
    ÑĩÑĥ
    0.16
    人éĹ´
    0.16
    CellStyle
    0.16
    Activations Density 0.009%

    No Known Activations