© 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. 12288
    Prev
    Next
    INDEX
    Explanations

    academic success

    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
    bread
    -0.21
    iders
    -0.17
    anmar
    -0.17
    ãģĦãģ¦
    -0.16
    -thirds
    -0.16
    anca
    -0.16
    onen
    -0.15
    alysis
    -0.15
    ãģĬãĤĬ
    -0.15
    aked
    -0.15
    POSITIVE LOGITS
    -minded
    0.27
    ALLY
    0.25
     minded
    0.23
    inte
    0.19
    iale
    0.19
    -cultural
    0.18
    妲
    0.18
    ãģĹãģ¾ãģĦ
    0.18
    ally
    0.17
    ural
    0.17
    Activations Density 0.011%

    No Known Activations