© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25538
    Prev
    Next
    INDEX
    Explanations

    Software licenses and URLs

    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
    Negative Logits
     https
    -0.98
    https
    -0.94
     http
    -0.92
    http
    -0.84
    :http
    -0.71
    	http
    -0.65
     www
    -0.62
    (http
    -0.58
    .http
    -0.57
    www
    -0.56
    POSITIVE LOGITS
    oge
    0.27
     Capcom
    0.26
    *num
    0.25
    黩
    0.25
    elter
    0.24
    è¶Ĭ好
    0.24
     vertically
    0.24
    suppress
    0.24
    umer
    0.23
    upp
    0.23
    Activations Density 0.042%

    No Known Activations