© 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. 22990
    Prev
    Next
    INDEX
    Explanations

    hospital

    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
    åĪ«
    -0.31
    match
    -0.29
    Matcher
    -0.28
    åĮ¹éħį
    -0.27
     Match
    -0.27
     matched
    -0.26
    顽
    -0.26
    è§ħ
    -0.26
     labour
    -0.26
    uliar
    -0.26
    POSITIVE LOGITS
    ewater
    0.26
    anged
    0.26
    idon
    0.26
    iband
    0.26
    ifs
    0.26
    atos
    0.25
    &B
    0.25
    eroon
    0.25
     naked
    0.24
    &D
    0.24
    Activations Density 0.004%

    No Known Activations