© 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. 14939
    Prev
    Next
    INDEX
    Explanations

    financial crisis and rescue plan

    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
    éģĹ
    -0.23
    éģº
    -0.23
    inherit
    -0.21
    cycles
    -0.19
    forced
    -0.19
    iable
    -0.19
    Intersection
    -0.19
    ç¿»
    -0.19
    rank
    -0.19
    ured
    -0.19
    POSITIVE LOGITS
    æģIJæħĮ
    0.24
    æµģåĬ¨æĢ§
    0.24
    个åĪ«
    0.23
    éĩijèŀįå¸Ĥåľº
    0.23
    稳å®ļ
    0.22
    æī©æķ£
    0.20
    è·Įå¹ħ
    0.20
    ç¼ĵåĨ²
    0.20
     stabil
    0.20
    渡
    0.20
    Activations Density 0.009%

    No Known Activations