© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    _specific contexts

    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
    èĸ°
    -0.24
    åıĤåĬłäºĨ
    -0.23
    å¢ŀè¿Ľ
    -0.23
    åİĭ
    -0.23
    黾
    -0.23
     PSP
    -0.22
    æľī两ç§į
    -0.22
    çĨı
    -0.22
    åıĤä¸İ
    -0.22
    ĶåĽŀ
    -0.21
    POSITIVE LOGITS
    _specific
    0.27
    contexts
    0.26
    pecific
    0.26
    ä½Ĩè¿Ļ
    0.24
     singled
    0.23
    itto
    0.22
     sola
    0.22
    æĶ¿åºľéĥ¨éŨ
    0.22
    examples
    0.22
    åıªè¦ģæĺ¯
    0.21
    Activations Density 0.050%

    No Known Activations