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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 151
    Prev
    Next
    INDEX
    Explanations

    musical intervals and code delimiters

    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
    uniform
    -0.25
    æĸĩ书
    -0.25
    Zip
    -0.24
     Tape
    -0.24
    Uniform
    -0.23
     manuscripts
    -0.23
    vern
    -0.23
    procedure
    -0.23
    Colon
    -0.23
    zip
    -0.23
    POSITIVE LOGITS
     opposite
    0.31
     oppos
    0.29
     distance
    0.29
    ä¸Ģ对
    0.28
    è·Ŀ离
    0.28
     thirds
    0.27
     between
    0.27
     BETWEEN
    0.27
    è·ĿéĽ¢
    0.26
    /rem
    0.26
    Activations Density 0.021%

    No Known Activations