© 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. 14520
    Prev
    Next
    INDEX
    Explanations

    San Jose, Hong Kong, York, Sturgeon Bay

    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
    anden
    -0.21
    访
    -0.20
     raised
    -0.19
    irl
    -0.19
    -Mart
    -0.18
    .Inner
    -0.18
     sealing
    -0.18
     года
    -0.18
    .bulk
    -0.18
     Merkel
    -0.18
    POSITIVE LOGITS
    è§Ĩ
    0.20
    åıijå¸ĥæŶéĹ´
    0.20
    åĮĹ京æŶéĹ´
    0.20
    çľĭçĶµè§Ĩ
    0.19
    çIJĨ解åĴĮ
    0.19
    æĴŃæĬ¥
    0.19
    é¢ĨåħĪçļĦ
    0.18
    åīįæīĢæľªæľī
    0.18
    åħ¨ç¨ĭ
    0.18
    æĴŃåĩº
    0.18
    Activations Density 0.032%

    No Known Activations