© 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. 3256
    Prev
    Next
    INDEX
    Explanations

    going through

    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
    ä¸įä½ı
    -0.25
     presence
    -0.22
    elong
    -0.21
    èĢĥèĻijåĪ°
    -0.21
     found
    -0.20
    istant
    -0.20
    scar
    -0.20
    é£ŀæī¬
    -0.20
    ¤í
    -0.20
    -seeking
    -0.20
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.30
    ä¸Ģç³»åĪĹ
    0.28
    èľķåıĺ
    0.27
    äºĨä¸Ģéģį
    0.27
    å®Į
    0.25
    ä¸įåIJĮç¨ĭ度
    0.24
    äºĨä¸Ģåľº
    0.24
    ä¸Ģéģį
    0.23
    /be
    0.23
    ä¸Ģåľº
    0.23
    Activations Density 0.028%

    No Known Activations