© 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. 15149
    Prev
    Next
    INDEX
    Explanations

    critical thinking and reasoning skills

    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
    室åĨħ
    -0.23
    俾
    -0.22
    æĮª
    -0.21
    illos
    -0.20
     civil
    -0.20
     Hü
    -0.19
    åIJĮå¿Ĺ们
    -0.18
     intimate
    -0.18
     civilized
    -0.18
    åĢŁ
    -0.18
    POSITIVE LOGITS
    æݨçIJĨ
    0.27
    èĥ½åĬĽ
    0.25
    èĥ½åĬĽåĴĮ
    0.24
    æĢĿç»´
    0.23
    éĢ»è¾ij
    0.23
     skills
    0.23
     logic
    0.22
     reasoning
    0.21
    çĿ¥
    0.20
    nelle
    0.20
    Activations Density 0.017%

    No Known Activations