© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11742
    Prev
    Next
    INDEX
    Explanations

    horror movie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    èĨĺ
    -0.22
    å¹³çŃī
    -0.22
     mirac
    -0.22
    裨
    -0.21
    åĵĤ
    -0.21
    èĹIJ
    -0.20
    åĢľ
    -0.20
    åĢ¨
    -0.20
    è°Ħ
    -0.20
    èħ¼
    -0.20
    POSITIVE LOGITS
    æģIJæĢĸ
    0.42
    æģIJæĥ§
    0.34
    é»ijæļĹ
    0.33
    dark
    0.31
    Dark
    0.30
     darkness
    0.29
     dark
    0.28
    åı¯æĢķçļĦ
    0.26
     fear
    0.26
     terror
    0.26
    Activations Density 0.109%

    No Known Activations