© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24037
    Prev
    Next
    INDEX
    Explanations

    basics

    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
    åŃ£èĬĤ
    -0.34
    screens
    -0.32
    èİ«
    -0.28
    æ½ľ
    -0.27
    ÑĮе
    -0.26
    éĻį
    -0.26
    æĹģ
    -0.25
     storms
    -0.25
    soap
    -0.25
    egen
    -0.25
    POSITIVE LOGITS
    å¼Ħå¾Ĺ
    0.27
     about
    0.26
     understandably
    0.26
     slamming
    0.26
     Hath
    0.25
    ets
    0.25
    oupper
    0.25
     hitting
    0.24
    etect
    0.24
     necessary
    0.23
    Activations Density 0.031%

    No Known Activations