© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 550
    Prev
    Next
    INDEX
    Explanations

    unique product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     public
    -0.28
    äºĭ件
    -0.27
     events
    -0.27
     tentative
    -0.27
    åŁºè°ĥ
    -0.27
    åĬ¨èį¡
    -0.26
     governance
    -0.26
     frameworks
    -0.26
     orchestrated
    -0.26
     abstract
    -0.26
    POSITIVE LOGITS
    éħį件
    0.50
     waterproof
    0.47
    èĢIJçĶ¨
    0.46
     patented
    0.43
    使çĶ¨å¯¿åij½
    0.43
    çļĦ产åĵģ
    0.42
    å¤ļåĬŁèĥ½
    0.42
     accessories
    0.42
     Waterproof
    0.42
    å®īè£ħ
    0.41
    Activations Density 0.230%

    No Known Activations