© 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. 11102
    Prev
    Next
    INDEX
    Explanations

    measure or estimate

    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
    £
    -0.22
    ãģ¡ãģ¯
    -0.17
    оÑģÑĮ
    -0.17
    ãĤĤãģĨ
    -0.17
    antes
    -0.16
    низ
    -0.16
    temps
    -0.16
    endum
    -0.16
    OrUpdate
    -0.16
    abouts
    -0.16
    POSITIVE LOGITS
    edImage
    0.17
    orda
    0.16
    ingly
    0.16
    erry
    0.15
    leep
    0.15
    OMETRY
    0.15
    ing
    0.15
    çļ¿
    0.15
    elin
    0.15
    WER
    0.15
    Activations Density 0.024%

    No Known Activations