© 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. 25-TRANSCODER-HP
    7. 108852
    Prev
    Next
    INDEX
    Explanations

    replacement or medical advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为æĪij们
    -0.26
     blitz
    -0.26
    âĦ
    -0.25
    opers
    -0.25
    пÑĥÑģ
    -0.25
    STATIC
    -0.25
    ç»´
    -0.24
    Simon
    -0.24
    thing
    -0.23
    .EVENT
    -0.23
    POSITIVE LOGITS
     close
    0.28
     reception
    0.28
     Close
    0.27
     Injury
    0.27
     photographs
    0.27
    ä¸įå¿į
    0.26
    ä¸įçĪ±
    0.26
     Recovery
    0.26
    .close
    0.25
     photo
    0.25
    Activations Density 0.028%

    No Known Activations