© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 878
    Prev
    Next
    INDEX
    Explanations

    with or and followed by noun

    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
     vert
    -0.26
    ropa
    -0.26
     appar
    -0.22
    è¿ŀäºij
    -0.21
    IfExists
    -0.21
     lesb
    -0.21
    å¼¯æĽ²
    -0.21
    çľ©
    -0.21
    åİĮ
    -0.21
    loud
    -0.21
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.27
     frac
    0.26
    ä¸ĢæĬĬ
    0.24
    第ä¸ĢæŃ¥
    0.24
     Brush
    0.23
     nan
    0.23
     fraction
    0.23
    ä¸ĢæŃ¥
    0.22
     *>
    0.22
     grains
    0.22
    Activations Density 0.002%

    No Known Activations