© 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
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161802
    Prev
    Next
    INDEX
    Explanations

    The number 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --*/↵
    -0.28
    loff
    -0.26
     borders
    -0.24
    âĶĢâĶĢ
    -0.24
    --č↵
    -0.24
    -->č↵
    -0.23
    ald
    -0.23
     '/';↵
    -0.23
     ';'
    -0.23
     subdiv
    -0.23
    POSITIVE LOGITS
    æĶ¾å¤§
    0.28
    æĭī
    0.28
    èIJ½å®ŀ
    0.27
    cing
    0.27
    ä¹ĭä¸Ĭ
    0.26
    á»ĭch
    0.26
    å´©
    0.25
    ä»ĭ
    0.25
    ê¸ĭ
    0.25
    rosso
    0.24
    Activations Density 0.008%

    No Known Activations