© 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. 3304
    Prev
    Next
    INDEX
    Explanations

    mixed results or reviews

    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
    erset
    -0.27
     testName
    -0.22
     blazing
    -0.22
    vit
    -0.22
    åĵªæĢķ
    -0.22
     vit
    -0.21
    vest
    -0.21
    çĥ§
    -0.20
     premises
    -0.20
    levation
    -0.20
    POSITIVE LOGITS
     depending
    0.47
    depending
    0.39
     Depending
    0.35
    Depending
    0.33
    好åĿı
    0.31
    ä¸įåIJĮçļĦ
    0.31
     whether
    0.30
    Whether
    0.29
    whether
    0.28
    çľĭå¾ħ
    0.27
    Activations Density 0.141%

    No Known Activations