© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14596
    Prev
    Next
    INDEX
    Explanations

    time, day, year, second, min

    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
    etic
    -0.23
    éĢŁ
    -0.23
    å¼Ĥ
    -0.20
    et
    -0.20
    è´º
    -0.19
    è¿°
    -0.19
    atti
    -0.18
    ä¸Ģéģĵ
    -0.18
    åĬ¨åĬĽ
    -0.18
    åĬŁ
    -0.18
    POSITIVE LOGITS
     Corporation
    0.20
    åħ¨å¤©
    0.18
    inces
    0.18
    MEA
    0.17
     Dodge
    0.17
    TECT
    0.17
    -SA
    0.17
    裾
    0.17
     BlackBerry
    0.17
    chedules
    0.17
    Activations Density 0.010%

    No Known Activations