© 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. 16790
    Prev
    Next
    INDEX
    Explanations

    available soon / takes only / open to

    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
    æ²³æµģåŁŁ
    -0.24
    è·ŁçĿĢ
    -0.21
    à¸Ĥà¸Ļา
    -0.20
    趺
    -0.19
    èĤĦ
    -0.18
     ÑĦл
    -0.18
    $__
    -0.17
    legg
    -0.17
    -builder
    -0.17
    trait
    -0.17
    POSITIVE LOGITS
    oggle
    0.27
    室å¤ĸ
    0.21
    Bindings
    0.19
    æīĢæľī人
    0.19
    vine
    0.18
    管çIJĨä¸Ńå¿ĥ
    0.18
    å¾ģæ±ĤæĦıè§ģ
    0.18
    缦
    0.18
    tab
    0.18
     bicy
    0.17
    Activations Density 0.001%

    No Known Activations