© 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. 11211
    Prev
    Next
    INDEX
    Explanations

    countertops and kitchen features

    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
    åĨ¢
    -0.19
    QObject
    -0.18
    éķ§
    -0.18
    ãģĺ
    -0.18
    ITAL
    -0.18
    åĴ¦
    -0.18
    ió
    -0.18
    "label
    -0.18
    ONGL
    -0.18
    åľ¨éĩĮéĿ¢
    -0.18
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.26
    榴
    0.20
    Advisor
    0.20
    -mounted
    0.19
    çĦķ
    0.18
    纪å§Ķ书记
    0.18
     countertops
    0.18
    容éĩı
    0.18
    ogle
    0.18
     GiriÅŁ
    0.18
    Activations Density 0.005%

    No Known Activations