© 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. 14604
    Prev
    Next
    INDEX
    Explanations

    derby or shire place names

    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
    liness
    -0.18
    usz
    -0.16
    è¿ĺä¸įå¦Ĥ
    -0.16
     Minute
    -0.15
    -0.15
    umed
    -0.15
    veral
    -0.15
    Ùĭ
    -0.15
    vanced
    -0.15
    ively
    -0.15
    POSITIVE LOGITS
    shire
    0.31
    ity
    0.26
    onian
    0.20
    è¡·
    0.18
    åĭĥåĭĥ
    0.18
    éģĦ
    0.17
    zeit
    0.17
    odont
    0.17
    zeug
    0.17
    ache
    0.17
    Activations Density 0.002%

    No Known Activations