© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2545
    Prev
    Next
    INDEX
    Explanations

    apparatus and method

    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
     NOTHING
    -0.27
     seper
    -0.25
    UNCH
    -0.23
    è¿Ļéĥ¨åĪĨ
    -0.23
    çľĭä¸įåĪ°
    -0.23
    ience
    -0.22
    æĭĽèĤ¡
    -0.22
     nothing
    -0.22
    忽
    -0.22
    PECIAL
    -0.22
    POSITIVE LOGITS
     apparatus
    0.40
    è£ħç½®
    0.29
     plurality
    0.27
    åħ·æľīèī¯å¥½
    0.25
     contemplated
    0.24
    çļĦéģĵè·¯
    0.24
    toy
    0.24
     nutshell
    0.24
    è£ħå¤ĩ
    0.24
    æľīè¿Ļæł·çļĦ
    0.24
    Activations Density 1.917%

    No Known Activations