© 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. 1931
    Prev
    Next
    INDEX
    Explanations

    horror film titles and actors

    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
     tán
    -0.27
    天æĸĩ
    -0.26
     ëĮĢíĨµ
    -0.24
    建档
    -0.23
    imps
    -0.23
    移æ°ij
    -0.22
    æ¾İ
    -0.22
    ç£ģ
    -0.22
    éra
    -0.22
    ä¼Ĭæĭī
    -0.22
    POSITIVE LOGITS
    æĿĢ人
    0.37
    è¡Ģèħ¥
    0.35
    æĿĢ
    0.32
    cth
    0.32
     killer
    0.30
    æĿĢ害
    0.30
    æ®ĭå¿į
    0.30
     deadly
    0.29
     death
    0.29
    æ¯Ĵ
    0.29
    Activations Density 0.029%

    No Known Activations