© 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. 24-TRANSCODER-HP
    7. 150171
    Prev
    Next
    INDEX
    Explanations

    Official reports and legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conferences
    -0.42
    ä¼ļè®®ä¸Ĭ
    -0.41
    ä¼ļè®®
    -0.40
    åı¬å¼Ģ
    -0.39
    çŃ¾ç½²
    -0.38
     conference
    -0.37
    çŃ¾ç½²äºĨ
    -0.37
     Conference
    -0.35
    conference
    -0.34
    çŃ¾è®¢
    -0.32
    POSITIVE LOGITS
    ={({
    0.28
    èīº
    0.27
     squared
    0.27
    _FIFO
    0.27
    [((
    0.26
    art
    0.25
    strain
    0.24
    ovan
    0.24
    ứ
    0.24
    ifer
    0.24
    Activations Density 0.912%

    No Known Activations