© 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. 23021
    Prev
    Next
    INDEX
    Explanations

    food

    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
    .linkedin
    -0.30
    交äºĴ
    -0.27
    åĽº
    -0.25
    yan
    -0.25
    交ç»ĩ
    -0.25
    åħ°èĬ±
    -0.24
    ión
    -0.24
    交
    -0.24
    .github
    -0.24
    å¦ĩ
    -0.24
    POSITIVE LOGITS
     вой
    0.29
    ordin
    0.27
    æķĻåŃ¦è´¨éĩı
    0.26
    åĨħ马
    0.26
     gul
    0.25
    .AutoScale
    0.25
    åĿ¼
    0.25
     percent
    0.25
    agnar
    0.25
    á»ĵi
    0.25
    Activations Density 0.000%

    No Known Activations