© 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. 2950
    Prev
    Next
    INDEX
    Explanations

    proposed methodology

    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
     tore
    -0.25
    äºĨä¸Ģä¸ĭ
    -0.24
     tear
    -0.23
    ç¿»å¼Ģ
    -0.23
    äºĨä¸ĢäºĽ
    -0.23
    äºĨä¸Ģæī¹
    -0.23
    äºĨä¸Ģåľº
    -0.23
    åĽŀæĥ³
    -0.23
     academics
    -0.22
    ød
    -0.22
    POSITIVE LOGITS
    æŃ¤é¡¹
    0.24
    æĢ§çļĦ
    0.23
     Nationwide
    0.23
    è¿Ļ项
    0.23
     impact
    0.22
    нÑĮ
    0.22
    ç¥ŀå¥ĩ
    0.22
     beta
    0.22
    该项
    0.21
     swell
    0.20
    Activations Density 0.148%

    No Known Activations