© 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. 9-TRANSCODER-HP
    7. 29253
    Prev
    Next
    INDEX
    Explanations

    Oxford

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ģç»ı
    -0.28
    onica
    -0.27
    walker
    -0.26
    mirror
    -0.25
    éķľ
    -0.25
    éı¡
    -0.25
    irror
    -0.24
    onders
    -0.24
    éķľå¤´
    -0.24
    agent
    -0.24
    POSITIVE LOGITS
    еÑĢи
    0.29
    lyph
    0.28
    uhan
    0.28
     chilling
    0.26
    blick
    0.26
    åĭĭ
    0.25
    oints
    0.25
    çľĭ
    0.24
    ringe
    0.24
    boards
    0.24
    Activations Density 0.190%

    No Known Activations