© 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. 15079
    Prev
    Next
    INDEX
    Explanations

    personal data fields

    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
     BaseType
    -0.20
    交æį¢
    -0.19
    VERS
    -0.19
    ONA
    -0.19
    éĽªå±±
    -0.18
    ighting
    -0.18
    顶å±Ĥ
    -0.18
     ÙĨÙģسÙĩا
    -0.17
    ENAME
    -0.17
    STOP
    -0.17
    POSITIVE LOGITS
    (optional
    0.20
    åħĸ
    0.19
    建档
    0.19
    æľĢ好æĺ¯
    0.18
    å½Ĵ
    0.18
    edm
    0.18
    çªŁ
    0.18
    جرÙĬ
    0.18
    éķĢ
    0.18
    æķĪåĬĽ
    0.17
    Activations Density 0.110%

    No Known Activations