© 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. 24-TRANSCODER-HP
    7. 151312
    Prev
    Next
    INDEX
    Explanations

    Code, license, technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    羣å¿ĥ
    -0.29
    è¯Ŀè¯ŃæĿĥ
    -0.28
     Kir
    -0.28
    åıĭåĸĦ
    -0.27
    IPAddress
    -0.26
    以人为
    -0.26
     nameof
    -0.25
     Kushner
    -0.25
    åĴĮå¹³
    -0.25
    zn
    -0.24
    POSITIVE LOGITS
     held
    0.30
    å¹³åı°ä¸Ĭ
    0.27
     format
    0.26
     along
    0.26
     fixed
    0.25
     Guidance
    0.25
    held
    0.25
    åijĪ
    0.25
    _fixed
    0.24
    æĮĩ导ä¸ĭ
    0.24
    Activations Density 0.917%

    No Known Activations