© 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. 23354
    Prev
    Next
    INDEX
    Explanations

    way

    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
    ither
    -0.28
    Ậ
    -0.26
    áf
    -0.26
     iÅŁlemleri
    -0.26
    larıyla
    -0.24
    骨骼
    -0.24
    _needed
    -0.23
    [counter
    -0.23
     owe
    -0.23
    åĦ¡
    -0.23
    POSITIVE LOGITS
    Computed
    0.25
    agan
    0.25
    íķĺìĭł
    0.24
    ä¸ĬæĬ¥
    0.24
    itelist
    0.24
    ä¸ĭ乡
    0.24
    \Routing
    0.23
    e
    0.23
    BITS
    0.23
     Entrance
    0.23
    Activations Density 0.004%

    No Known Activations