© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22484
    Prev
    Next
    INDEX
    Explanations

    Technology and medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çľĩ
    -0.32
    (exports
    -0.28
    ores
    -0.28
    (/^
    -0.27
    éŨåīį
    -0.26
    etes
    -0.25
    xEE
    -0.25
    ORS
    -0.24
     semen
    -0.24
    efs
    -0.24
    POSITIVE LOGITS
    tron
    0.30
     tro
    0.29
    izon
    0.28
    tro
    0.27
     Tro
    0.26
    éļı
    0.25
    ustral
    0.25
    Tro
    0.24
     unk
    0.24
    stacle
    0.24
    Activations Density 0.012%

    No Known Activations