© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    ISBN or copyright notices

    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
    è´·
    -0.21
    pseudo
    -0.20
    个人信æģ¯
    -0.19
    .ke
    -0.19
    åĬłåĢį
    -0.19
    å¥ĩ
    -0.19
    cons
    -0.19
     krótk
    -0.18
    ered
    -0.18
    posted
    -0.18
    POSITIVE LOGITS
    å»Ľ
    0.21
    å¥Ĺè£ħ
    0.20
    æİı
    0.20
    èĻ±
    0.19
    ä¸ĭè°ĥ
    0.19
     sodom
    0.19
     Vish
    0.19
    èĴº
    0.18
    è¿ĪåIJij
    0.18
    åĭĺ
    0.18
    Activations Density 0.021%

    No Known Activations