© 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. 2324
    Prev
    Next
    INDEX
    Explanations

    story and fiction writing

    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
    æĹº
    -0.27
    enus
    -0.24
    asca
    -0.23
    éŨæĪ·
    -0.22
    æĸ°æĶ¿
    -0.22
    rage
    -0.22
     wash
    -0.22
    西è£ħ
    -0.22
    ahan
    -0.21
    wash
    -0.21
    POSITIVE LOGITS
    å°ı说
    0.40
    å°ı說
    0.35
    è¿ŀè½½
    0.34
    /story
    0.33
     narratives
    0.32
     narrative
    0.32
    æķħäºĭ
    0.31
     stories
    0.31
    .story
    0.31
     tales
    0.30
    Activations Density 0.036%

    No Known Activations