© 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. 162949
    Prev
    Next
    INDEX
    Explanations

    Difficulty

    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
    åĹ£
    -0.26
    åĬ¨æľº
    -0.26
    ä¸Ģéģĵ
    -0.25
    竹
    -0.25
    åħ·ä½ĵæĥħåĨµ
    -0.25
    bam
    -0.25
    ighton
    -0.25
    éĹ¾
    -0.25
    秣éĩij
    -0.24
    ç¨İçİĩ
    -0.24
    POSITIVE LOGITS
     comp
    0.27
     concept
    0.26
    æ¸ļ
    0.26
    æĥij
    0.26
    æĸ°éĹ»ç½ij
    0.26
    unker
    0.26
    ingham
    0.26
    WebpackPlugin
    0.24
    gger
    0.24
    ến
    0.24
    Activations Density 0.011%

    No Known Activations