© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3356
    Prev
    Next
    INDEX
    Explanations

    felony, murder, assault, capital, aggravated

    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
    Negative Logits
    zen
    -0.26
    人å¿ĥ
    -0.24
    è¿Ļä¸Ģ
    -0.22
    orne
    -0.22
    needle
    -0.22
     ÑģÑĤоÑĢон
    -0.22
    æ¸ħæ¾Ī
    -0.21
    clip
    -0.21
    obil
    -0.21
    (tol
    -0.21
    POSITIVE LOGITS
    ød
    0.26
     treason
    0.23
     crime
    0.22
    èµ°ç§ģ
    0.22
     theft
    0.22
     Fla
    0.22
    çĬ¯ç½ª
    0.22
     Conce
    0.21
     reverse
    0.21
     smuggling
    0.21
    Activations Density 0.006%

    No Known Activations