© 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. 11391
    Prev
    Next
    INDEX
    Explanations

    bending materials

    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
    sic
    -0.18
    YTE
    -0.17
    aat
    -0.16
    cade
    -0.16
    yes
    -0.16
    ye
    -0.16
    acter
    -0.16
    antas
    -0.16
    Ń
    -0.16
    atic
    -0.15
    POSITIVE LOGITS
    rok
    0.21
    åĦ¿
    0.19
    tures
    0.18
    pipe
    0.18
    ë¥ĺ
    0.17
    ning
    0.17
    rove
    0.17
    èĩªå¦Ĥ
    0.17
    est
    0.17
     tÆ°á»Ŀng
    0.17
    Activations Density 0.004%

    No Known Activations