© 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. 15132
    Prev
    Next
    INDEX
    Explanations

    old or existing

    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
    éĻį临
    -0.21
    ipay
    -0.21
    appropri
    -0.20
    大èĦij
    -0.20
    æ¯ĽåŃĶ
    -0.19
     appropriately
    -0.19
    å²ĺ
    -0.19
    è¿ĩåī©
    -0.19
     qp
    -0.19
    NM
    -0.19
    POSITIVE LOGITS
    åİŁæĿ¥çļĦ
    0.38
    åİŁæľīçļĦ
    0.35
    åİŁæľī
    0.34
    æŧ
    0.33
     previous
    0.29
     existing
    0.27
     old
    0.27
    (old
    0.26
    åİŁæĿ¥
    0.25
    .old
    0.25
    Activations Density 0.118%

    No Known Activations