© 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. 27-TRANSCODER-HP
    7. 7843
    Prev
    Next
    INDEX
    Explanations

    Dates and events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     POT
    -0.29
    两个å°ıæŶ
    -0.27
     pot
    -0.27
     disg
    -0.26
    ISR
    -0.26
    羿
    -0.25
     discourse
    -0.25
    .inc
    -0.25
    isable
    -0.24
    港åĮº
    -0.24
    POSITIVE LOGITS
    allet
    0.31
    à°¦
    0.26
    MENTS
    0.26
    åıijè¾¾åĽ½å®¶
    0.25
    ovel
    0.25
    xmm
    0.25
    æ°´å¹³
    0.24
    auses
    0.24
    oved
    0.24
    GUID
    0.24
    Activations Density 0.004%

    No Known Activations