© 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. 23459
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    mó
    -0.30
     Conspiracy
    -0.28
    .space
    -0.26
    å·²ç»ıè¾¾åĪ°
    -0.26
    èĭĩ
    -0.26
    åĮĹæĸĹ
    -0.25
    actively
    -0.24
    riters
    -0.24
    çĩİ
    -0.24
    bw
    -0.24
    POSITIVE LOGITS
     Note
    0.29
     said
    0.28
     Raises
    0.28
     Chapter
    0.27
     note
    0.27
    Chapter
    0.27
     ...
    0.26
     phil
    0.26
     angel
    0.26
     Ack
    0.26
    Activations Density 0.009%

    No Known Activations