© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    intensifiers or descriptors

    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
     займ
    -0.24
    .aspx
    -0.23
    ãģ§ãģĹãĤĩãģĨ
    -0.23
    hel
    -0.22
    -column
    -0.22
     lad
    -0.22
     sollen
    -0.22
    anda
    -0.22
     hopefully
    -0.21
     uda
    -0.21
    POSITIVE LOGITS
    æ¯ĶæĪij
    0.45
    æĪijåıijçİ°
    0.42
     surprisingly
    0.36
    æŀľçĦ¶
    0.36
    ç»ĻæĪij
    0.35
    ç»ĻäºĨæĪij
    0.34
    æĪijå½ĵæŶ
    0.34
    æĪijè§īå¾Ĺ
    0.33
    çļĦæĦŁè§ī
    0.33
    羣çļĦå¾Ī
    0.33
    Activations Density 0.183%

    No Known Activations