© 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. 14-TRANSCODER-HP
    7. 40457
    Prev
    Next
    INDEX
    Explanations

    reasonable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irth
    -0.29
    çĮ·
    -0.26
    ivable
    -0.26
    éĨ®
    -0.26
    âĹĪ
    -0.25
    ONY
    -0.25
     Gratuit
    -0.24
    umes
    -0.24
    posable
    -0.24
    鼷æĸ¯
    -0.24
    POSITIVE LOGITS
     bus
    0.27
     deposits
    0.26
    .svg
    0.25
    çīĻ
    0.25
    _BUS
    0.25
    ellig
    0.25
     restarting
    0.25
    aling
    0.25
    business
    0.24
     bitten
    0.24
    Activations Density 2.197%

    No Known Activations