© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2925
    Prev
    Next
    INDEX
    Explanations

    series titles and technical terms

    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
    éĻµ
    -0.26
    女æĸ¹
    -0.26
     champagne
    -0.26
    驾
    -0.25
     transgender
    -0.24
     trance
    -0.24
    æĹ¥äº§
    -0.24
    ä¸ĩåı°
    -0.23
    泡
    -0.23
     trillion
    -0.23
    POSITIVE LOGITS
    å¯Įæ°ij
    0.26
     rust
    0.25
    Bird
    0.25
     Bird
    0.24
     Job
    0.24
    è¿ŀäºij
    0.23
    lung
    0.23
     bird
    0.23
    绿åĮĸ
    0.23
    åŁºç«Ļ
    0.23
    Activations Density 0.194%

    No Known Activations