© 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. 30-TRANSCODER-HP
    7. 96980
    Prev
    Next
    INDEX
    Explanations

    seeing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     !_
    -0.28
    ham
    -0.28
    FileDialog
    -0.25
    _Resource
    -0.25
     hij
    -0.25
    .foreach
    -0.25
    HAM
    -0.25
     resource
    -0.25
     partition
    -0.24
     ham
    -0.24
    POSITIVE LOGITS
     seeing
    0.37
    seeing
    0.32
    è§ģ
    0.32
     see
    0.31
    çľĭåĪ°
    0.31
    çľĭè§ģ
    0.31
    see
    0.30
     sees
    0.30
    è§ģåĪ°
    0.29
    See
    0.29
    Activations Density 0.104%

    No Known Activations