© 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. 162780
    Prev
    Next
    INDEX
    Explanations

    Code/technical snippets

    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
     needless
    -0.31
    æĢ§å¼º
    -0.27
    eel
    -0.27
    dess
    -0.26
    StateException
    -0.25
    eton
    -0.25
    èĩªæĿ¥
    -0.25
    ificant
    -0.24
    ifton
    -0.24
    èĥ½åĬĽå¼º
    -0.24
    POSITIVE LOGITS
     ses
    0.26
    apr
    0.26
    chio
    0.25
    alt
    0.25
    æ¾ľ
    0.25
    airie
    0.25
    Deposit
    0.23
    ses
    0.23
    uses
    0.23
    å¹¼ç¨ļ
    0.23
    Activations Density 0.012%

    No Known Activations