© 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. 32-TRANSCODER-HP
    7. 43849
    Prev
    Next
    INDEX
    Explanations

    cro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bar
    -0.35
    bars
    -0.32
     bar
    -0.32
     bars
    -0.29
    æļĤ
    -0.28
    ail
    -0.28
    Bar
    -0.28
    ause
    -0.27
     Bar
    -0.27
    abl
    -0.27
    POSITIVE LOGITS
     Rouge
    0.26
    åīįç½®
    0.26
     Junk
    0.25
    çħ§äº®
    0.24
    rophe
    0.24
    宽æĿ¾
    0.24
    ertools
    0.24
    _logger
    0.24
    iguous
    0.24
     hindsight
    0.24
    Activations Density 0.001%

    No Known Activations