© 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. 25609
    Prev
    Next
    INDEX
    Explanations

    technical/instructional documents

    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
    çļĦè¯Ŀé¢ĺ
    -0.24
    çĶŁäº§å·¥èīº
    -0.24
    isl
    -0.24
     politic
    -0.23
    ils
    -0.23
     Policies
    -0.23
    .sun
    -0.23
     dlg
    -0.23
    (provider
    -0.23
    chal
    -0.23
    POSITIVE LOGITS
    å®ŀè·µ
    0.47
    å®ŀè·µç»ıéªĮ
    0.45
     experience
    0.44
    è§Ĥå¯Ł
    0.43
     experiences
    0.43
    å®ŀè·µä¸Ń
    0.43
     observations
    0.42
    ç»ıéªĮ
    0.41
     observed
    0.40
    çļĦç»ıéªĮ
    0.40
    Activations Density 0.002%

    No Known Activations