© 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. 31-TRANSCODER-HP
    7. 18023
    Prev
    Next
    INDEX
    Explanations

    close monitoring, observation, control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     close
    -0.32
     strict
    -0.31
     tight
    -0.31
    tight
    -0.29
    ä¸¥æł¼
    -0.29
     strictly
    -0.28
    ãģıãĤĮ
    -0.27
    æ··
    -0.27
     Close
    -0.27
    strict
    -0.27
    POSITIVE LOGITS
     coverage
    0.25
    (PC
    0.24
    注
    0.24
    airs
    0.24
    åĽ¢
    0.23
    uche
    0.23
    limits
    0.23
    ounds
    0.23
     rozp
    0.23
    à¸Ńà¸ģ
    0.23
    Activations Density 0.784%

    No Known Activations