© 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. 3038
    Prev
    Next
    INDEX
    Explanations

    in followed by month or date

    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
    æľīçĶ¨
    -0.25
    ä¸Ģå¤ľ
    -0.24
    åIJ¸
    -0.24
    产ä¸ļç»ĵæŀĦ
    -0.23
    LICENSE
    -0.22
    createCommand
    -0.22
     TRUE
    -0.22
    озв
    -0.22
     hack
    -0.22
     createAction
    -0.21
    POSITIVE LOGITS
    åį³å°ĨåĪ°æĿ¥
    0.28
    mid
    0.27
    abouts
    0.27
     soon
    0.27
     ÑģкоÑĢо
    0.27
    ä¸įåĪ°
    0.26
    åĪĨéĴŁå·¦åı³
    0.26
     mid
    0.26
    åį³å°Ĩ
    0.25
    鸽
    0.24
    Activations Density 0.029%

    No Known Activations